{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T21:38:20Z","timestamp":1770932300848,"version":"3.50.1"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0162101"],"award-info":[{"award-number":["2022ZD0162101"]}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["22DZ2229005"],"award-info":[{"award-number":["22DZ2229005"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/jstsp.2025.3568224","type":"journal-article","created":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T13:44:22Z","timestamp":1747057462000},"page":"1279-1290","source":"Crossref","is-referenced-by-count":0,"title":["Reconstruct the Pruned Model Without Retraining"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4331-9318","authenticated-orcid":false,"given":"Pingjie","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziqing","family":"Fan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6860-2222","authenticated-orcid":false,"given":"Shengchao","family":"Hu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4599-1170","authenticated-orcid":false,"given":"Zhe","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3196-2347","authenticated-orcid":false,"given":"Yanfeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9500-081X","authenticated-orcid":false,"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GLM-130b: An open bilingual pre-trained model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zeng","year":"2023"},{"key":"ref2","article-title":"Bloom: A 176b-parameter open-access multilingual language model","author":"Scao","year":"2022"},{"issue":"240","key":"ref3","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3334614"},{"key":"ref5","first-page":"24101","article-title":"A fast post-training pruning framework for transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Kwon","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.28960"},{"key":"ref7","article-title":"Gradient-free structured pruning with unlabeled data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nova","year":"2023"},{"key":"ref8","article-title":"Pruning filters for efficient convnets","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2017"},{"key":"ref9","article-title":"SNIP: Single-shot network pruning based on connection sensitivity","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee","year":"2019"},{"key":"ref10","article-title":"The LLM Surgeon","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ouderaa","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref12","first-page":"598","article-title":"Optimal brain damage","volume-title":"Advances in Neural Information Processing Systems","volume":"2","author":"LeCun","year":"1989"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1993.298572"},{"key":"ref14","article-title":"The state of sparsity in deep neural networks","author":"Gale","year":"2019"},{"key":"ref15","article-title":"A simple and effective pruning approach for large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sun","year":"2024"},{"key":"ref16","first-page":"10323","article-title":"Sparsegpt: Massive language models can be accurately pruned in one-shot","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Frantar","year":"2023"},{"key":"ref17","article-title":"Reducing transformer depth on demand with structured dropout","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fan","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1580"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1441"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.829"},{"key":"ref21","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Han","year":"2016"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.279"},{"key":"ref23","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref24","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref25","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref26","article-title":"GPT3.int8(): 8-bit matrix multiplication for transformers at scale","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Dettmers","year":"2022"},{"key":"ref27","article-title":"GPTQ: Accurate post-training quantization for generative pre-trained transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Frantar","year":"2022"},{"key":"ref28","article-title":"BRECQ: Pushing the limit of post-training quantization by block reconstruction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref30","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref31","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref32","article-title":"The Llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2124"},{"key":"ref36","article-title":"Pointer sentinel mixture models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Merity"},{"key":"ref37","article-title":"BoolQ: Exploring the surprising difficulty of natural yes\/no questions","author":"Clark","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1472"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3474381"},{"key":"ref41","article-title":"Think you have solved question answering? try arc, the ai2 reasoning challenge","author":"Clark","year":"2018"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1260"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1101"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480095"},{"key":"ref45","first-page":"552","article-title":"The winograd schema challenge","volume-title":"Proc. 13th Int. Conf. Principles Knowledge Representation Reasoning","author":"Levesque","year":"2012"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/11736790_9"},{"key":"ref47","first-page":"785","article-title":"The second pascal recognising textual entailment challenge","volume-title":"Proc. 2nd PASCAL Challenges Workshop Recognising Textual Entailment","volume":"7","author":"Haim","year":"2006"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3115\/1654536.1654538"},{"key":"ref49","article-title":"The fifth pascal recognizing textual entailment challenge","volume-title":"Proc. 2nd Text Anal. Conf.","author":"Bentivogli","year":"2009"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1170"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00290"},{"key":"ref52","article-title":"First quora dataset release: Question pairs","author":"Shankar","year":"2017"},{"key":"ref53","first-page":"9","article-title":"Automatically constructing a corpus of sentential paraphrases","volume-title":"Proc. Third Int. Workshop Paraphrasing","author":"Dolan","year":"2005"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S17-2001"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21236\/ADA273556"},{"key":"ref56","article-title":"Stanford alpaca: An instruction-following llama model","author":"Taori","year":"2023"},{"key":"ref57","article-title":"LLM-pruner: On the structural pruning of large language models","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Ma","year":"2023"},{"key":"ref58","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90% chatgpt quality","author":"Chiang","year":"2023"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4200690\/11320985\/11002425.pdf?arnumber=11002425","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T20:59:47Z","timestamp":1770929987000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11002425\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":60,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2025.3568224","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}