{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T05:24:54Z","timestamp":1787203494240,"version":"build-2736575974"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"U.S. Department of Energy"},{"name":"Office of Science"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/ipdpsw71298.2026.00108","type":"proceedings-article","created":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T19:13:45Z","timestamp":1787166825000},"page":"651-658","source":"Crossref","is-referenced-by-count":0,"title":["Generalizing Scaling Laws for Dense and Sparse Large Language Models"],"prefix":"10.1109","author":[{"given":"Md Arafat","family":"Hossain","sequence":"first","affiliation":[{"name":"Iowa State University","department":["Department of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingfu","family":"Wu","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Valerie","family":"Taylor","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Jannesari","sequence":"additional","affiliation":[{"name":"Iowa State University","department":["Department of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref3","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","article-title":"A survey on deep neural network pruning \u2013 taxonomy, comparison","author":"Cheng","year":"2023","journal-title":"Analysis, and Recommendations"},{"key":"ref5","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017","journal-title":"arXiv preprint arXiv:1701.06538"},{"key":"ref6","article-title":"Scaling language models: Methods, analysis & insights from training gopher","author":"Rae","year":"2021","journal-title":"arXiv preprint arXiv:2112.11446"},{"key":"ref7","article-title":"Using Deep-Speed and Megatron to train Tegatron-Turing NLG 530b, a large-scale generative language model","author":"Smith","year":"2022","journal-title":"arXiv preprint arXiv:2201.11990"},{"key":"ref8","article-title":"Lamda: Language models for dialog applications","author":"Thoppilan","year":"2022","journal-title":"arXiv preprint arXiv:2201.08239"},{"issue":"240","key":"ref9","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref10","article-title":"2 OLMo 2 Furious","author":"OLMo","year":"2024","journal-title":"arXiv preprint arXiv:2501.00656"},{"key":"ref11","article-title":"Generating long sequences with sparse transformers","author":"Child","year":"2019","journal-title":"arXiv preprint arXiv:1904.10509"},{"key":"ref12","first-page":"5547","article-title":"Glam: Efficient scaling of language models with mixture-of-experts","volume-title":"International Conference on Machine Learning","author":"Du"},{"issue":"120","key":"ref13","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW55747.2022.00171"},{"key":"ref15","article-title":"Olmoe: Open mixture-of-experts language models","author":"Muennighoff","year":"2024","journal-title":"arXiv preprint arXiv:2409.02060"},{"key":"ref16","article-title":"DeepSeek-v2: A strong, economical, and efficient mixture-of-experts language model","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv:2405.04434"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.70"},{"key":"ref18","article-title":"Mixtral of experts","author":"Jiang","year":"2024","journal-title":"arXiv preprint arXiv:2401.04088"},{"key":"ref19","article-title":"DeepSeek-r1: Incentivizing reasoning capability in LLMs via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv preprint arXiv:2501.12948"},{"issue":"8","key":"ref20","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref21","article-title":"DeepSeek-V3 technical report","year":"2025"},{"key":"ref22","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020","journal-title":"arXiv preprint arXiv:2001.08361"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2176"},{"key":"ref24","article-title":"Scaling laws for sparsely-connected foundation models","author":"Frantar","year":"2023","journal-title":"arXiv preprint arXiv:2309.08520"},{"key":"ref25","article-title":"Parameters vs flops: Scaling laws for optimal sparsity for mixture-of-experts language models","author":"Abnar","year":"2025","journal-title":"arXiv preprint arXiv:2501.12370"},{"key":"ref26","article-title":"Scaling laws for autoregressive generative modeling","author":"Henighan","year":"2020","journal-title":"arXiv preprint arXiv:2010.14701"},{"key":"ref27","first-page":"4057","article-title":"Unified scaling laws for routed language models","volume-title":"International Conference on Machine Learning","author":"Clark"},{"key":"ref28","article-title":"Scaling laws for fine-grained mixture of experts","volume-title":"Forty-first International Conference on Machine Learning","author":"Ludziejewski"},{"key":"ref29","article-title":"Language models scale reliably with over-training and on downstream tasks","author":"Gadre","year":"2024","journal-title":"arXiv preprint arXiv:2403.08540"},{"key":"ref30","article-title":"Scaling laws for precision","author":"Kumar","year":"2024","journal-title":"arXiv preprint arXiv:2411.04330"},{"key":"ref31","article-title":"Distillation scaling laws","author":"Busbridge","year":"2025"},{"key":"ref32","article-title":"Scaling law for quantization-aware training","author":"Chen","year":"2025","journal-title":"arXiv preprint arXiv:2505.14302"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1644"},{"key":"ref34","article-title":"Efficient autoregressive audio modeling via next-scale prediction","author":"Qiu","year":"2024","journal-title":"arXiv preprint arXiv:2408.09027"},{"key":"ref35","first-page":"265","article-title":"Scaling laws for generative mixed-modal language models","volume-title":"International Conference on Machine Learning","author":"Aghajanyan"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.8322"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1177\/10943420241286476"},{"key":"ref38","article-title":"ytopt: machine-learning-based autotuning and hyperparameter optimization framework using Bayesian Optimization","author":"Wu","year":"2025"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3626079"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3082815"},{"key":"ref41","article-title":"Q-sparse: All large language models can be fully sparsely-activated","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv:2407.10969"},{"key":"ref42","first-page":"2134","article-title":"SPDF: Sparse pre-training and dense fine-tuning for large language models","volume-title":"Uncertainty in Artificial Intelligence.","author":"Thangarasa","year":"2023"},{"key":"ref43","article-title":"Beyond Chinchilla-Optimal: Accounting for inference in language model scaling laws","author":"Sardana","year":"2025"}],"event":{"name":"2026 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","location":"New Orleans, LA, USA","start":{"date-parts":[[2026,5,25]]},"end":{"date-parts":[[2026,5,29]]}},"container-title":["2026 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11651886\/11651887\/11652023.pdf?arnumber=11652023","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T04:53:43Z","timestamp":1787201623000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11652023\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/ipdpsw71298.2026.00108","relation":{},"subject":[],"published":{"date-parts":[[2026,5]]}}}