{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T06:13:10Z","timestamp":1758089590729,"version":"3.44.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"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":[[2025,6,22]]},"DOI":"10.1109\/dac63849.2025.11133200","type":"proceedings-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T17:35:41Z","timestamp":1757957741000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["SSFT: Algorithm and Hardware Co-design for Structured Sparse Fine-Tuning of Large Language Models"],"prefix":"10.1109","author":[{"given":"Miao","family":"Yu","sequence":"first","affiliation":[{"name":"National University of Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Trevor E.","family":"Carlson","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","volume-title":"arXiv preprint arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.125"},{"key":"ref3","article-title":"Scaling sparse fine-tuning to large language models","author":"Ansell","year":"2024","journal-title":"arXiv preprint arXiv:2401.16405"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.1"},{"key":"ref5","article-title":"Evaluating large language models trained on code","author":"Chen","year":"2021","journal-title":"arXiv preprint arXiv:2107.03374"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00317"},{"key":"ref7","article-title":"QLoRA: Efficient finetuning of quantized llms","volume":"36","author":"Dettmers","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv:1810.04805"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2018.2832607"},{"key":"ref10","article-title":"Measuring massive multitask language understanding","author":"Hendrycks","year":"2020","journal-title":"arXiv preprint arXiv:2009.03300"},{"article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu","key":"ref11"},{"key":"ref12","article-title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning","author":"Lialin","year":"2023","journal-title":"arXiv preprint arXiv:2303.15647"},{"key":"ref13","first-page":"1950","article-title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning","volume":"35","author":"Liu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","first-page":"22631","article-title":"The flan collection: Designing data and methods for effective instruction tuning","volume-title":"International Conference on Machine Learning","author":"Longpre"},{"article-title":"PEFT: State-of-the-art parameter-efficient fine-tuning methods","year":"2022","author":"Mangrulkar","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2018.00013"},{"key":"ref17","article-title":"Instruction tuning with GPT-4","author":"Peng","year":"2023","journal-title":"arXiv preprint arXiv:2304.03277"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530585"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00015"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2023.3305569"},{"key":"ref21","first-page":"24 193","article-title":"Training neural networks with fixed sparse masks","volume":"34","author":"Sung","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2307.09288"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3273992"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tcad.2023.3283443"},{"key":"ref25","article-title":"Well-read students learn better: On the importance of pre-training compact models","author":"Turc","year":"2019","journal-title":"arXiv preprint arXiv:1908.08962"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00082"}],"event":{"name":"2025 62nd ACM\/IEEE Design Automation Conference (DAC)","start":{"date-parts":[[2025,6,22]]},"location":"San Francisco, CA, USA","end":{"date-parts":[[2025,6,25]]}},"container-title":["2025 62nd ACM\/IEEE Design Automation Conference (DAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11132383\/11132091\/11133200.pdf?arnumber=11133200","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T05:31:46Z","timestamp":1758000706000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11133200\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/dac63849.2025.11133200","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}