{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T03:34:20Z","timestamp":1777952060255,"version":"3.51.4"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":31,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Procedia Computer Science"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1016\/j.procs.2026.01.105","type":"journal-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T19:30:19Z","timestamp":1774035019000},"page":"923-930","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Sparse Mixture-of-Experts Transformers for Efficient Scaling of Large Language Models"],"prefix":"10.1016","volume":"275","author":[{"given":"Taher M.","family":"Ghazal","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"1\u20132","key":"10.1016\/j.procs.2026.01.105_bib1","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1108\/LM-06-2024-0065","article-title":"\u201cTAM and IS success model on digital library use, user satisfaction and net benefits: Indonesian open university context,\u201d","volume":"46","author":"Riady","year":"2025","journal-title":"Library Management"},{"issue":"1","key":"10.1016\/j.procs.2026.01.105_bib2","doi-asserted-by":"crossref","first-page":"1095","DOI":"10.32604\/iasc.2023.031335","article-title":"\u201cAI-Based Intelligent Model to Predict Epidemics Using Machine Learning Technique,\u201d","volume":"36","author":"Ali","year":"2023","journal-title":"Intelligent Automation & Soft Computing"},{"key":"10.1016\/j.procs.2026.01.105_bib3","doi-asserted-by":"crossref","unstructured":"T. K. Alhasan, \u201cLinguistic Proficiency Disclosures in International Arbitration: Enhancing Fairness and Efficiency,\u201d International Journal for the Semiotics of Law, 2025, doi: 10.1007\/s11196-025-10261-4.","DOI":"10.1007\/s11196-025-10261-4"},{"issue":"4","key":"10.1016\/j.procs.2026.01.105_bib4","doi-asserted-by":"crossref","first-page":"811","DOI":"10.1177\/02666669211054188","article-title":"\u201cDigitally Transforming Electronic Governments into Smart Governments: SMARTGOV, an Extended Maturity Model,\u201d","volume":"39","author":"Hujran","year":"2021","journal-title":"Information Development"},{"issue":"3","key":"10.1016\/j.procs.2026.01.105_bib5","doi-asserted-by":"crossref","first-page":"539","DOI":"10.32604\/iasc.2021.018888","article-title":"\u201cModeling Habit Patterns Using Conditional Reflexes in Agency,\u201d","volume":"29","author":"Khan","year":"2021","journal-title":"Intelligent Automation & Soft Computing"},{"issue":"3","key":"10.1016\/j.procs.2026.01.105_bib6","doi-asserted-by":"crossref","first-page":"893","DOI":"10.17507\/tpls.1403.32","article-title":"\u201cThe Phonological Features of Arabic Spoken by Non-Arabs in the UAE,\u201d","volume":"14","author":"Alsaifi","year":"2024","journal-title":"Theory and Practice in Language Studies"},{"key":"10.1016\/j.procs.2026.01.105_bib7","doi-asserted-by":"crossref","unstructured":"C. Dhasaratha et al., \u201cData privacy model using blockchain reinforcement federated learning approach for scalable internet of medical things,\u201d CAAI Trans Intell Technol, Feb. 2024, doi: 10.1049\/cit2.12287.","DOI":"10.1049\/cit2.12287"},{"issue":"3","key":"10.1016\/j.procs.2026.01.105_bib8","doi-asserted-by":"crossref","first-page":"627","DOI":"10.34028\/iajit\/22\/3\/15","article-title":"\u201cAgile Proactive Cybercrime Evidence Analysis Model for Digital Forensics,\u201d","volume":"22","author":"Al-Mousa","year":"2025","journal-title":"International Arab Journal of Information Technology"},{"key":"10.1016\/j.procs.2026.01.105_bib9","doi-asserted-by":"crossref","unstructured":"S. Abbas et al., \u201cFused Weighted Federated Deep Extreme Machine Learning Based on Intelligent Lung Cancer Disease Prediction Model for Healthcare 5.0,\u201d International Journal of Intelligent Systems, vol. 2023, no. 1, Jan. 2023, doi: 10.1155\/2023\/2599161.","DOI":"10.1155\/2023\/2599161"},{"issue":"4","key":"10.1016\/j.procs.2026.01.105_bib10","doi-asserted-by":"crossref","first-page":"508","DOI":"10.3390\/automation5040029","article-title":"\u201cLeveraging Multimodal Large Language Models (MLLMs) for Enhanced Object Detection and Scene Understanding in Thermal Images for Autonomous Driving Systems,\u201d","volume":"5","author":"Ashqar","year":"2024","journal-title":"Automation"},{"issue":"2","key":"10.1016\/j.procs.2026.01.105_bib11","doi-asserted-by":"crossref","first-page":"2579","DOI":"10.32604\/cmc.2022.019706","article-title":"\u201cIoMT-Enabled Fusion-Based Model to Predict Posture for Smart Healthcare Systems,\u201d","volume":"71","author":"Ghazal","year":"2022","journal-title":"Computers, Materials & Continua"},{"issue":"1","key":"10.1016\/j.procs.2026.01.105_bib12","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1111\/bju.16319","article-title":"\u201cThe optimal number of induction chemotherapy cycles in clinically lymph node-positive bladder cancer,\u201d","volume":"134","author":"von Deimling","year":"2024","journal-title":"BJU Int"},{"key":"10.1016\/j.procs.2026.01.105_bib13","doi-asserted-by":"crossref","unstructured":"S. Jaradat, T. I. Alhadidi, H. I. Ashqar, A. Hossain, and M. Elhenawy, \u201cExploring Traffic Crash Narratives in Jordan Using Text Mining Analytics,\u201d 2024, IEEE. doi: 10.1109\/ICMI60790.2024.10586010.","DOI":"10.1109\/ICMI60790.2024.10586010"},{"issue":"1","key":"10.1016\/j.procs.2026.01.105_bib14","first-page":"5547","article-title":"\u201cGlam: Efficient scaling of language models with mixture-of-experts., \u201d","volume":"2","author":"Du","year":"2022","journal-title":"In International conference on machine learning"},{"issue":"1","key":"10.1016\/j.procs.2026.01.105_bib15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TKDE.2025.3554028","article-title":"\u201cA survey on mixture of experts in large language models.,\u201d","volume":"2","author":"Cai","year":"2025","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"2","key":"10.1016\/j.procs.2026.01.105_bib16","first-page":"8583","article-title":"\u201cScaling vision with sparse mixture of experts.,\u201d","volume":"1","author":"Riquelme","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"issue":"2","key":"10.1016\/j.procs.2026.01.105_bib17","doi-asserted-by":"crossref","first-page":"3690","DOI":"10.1145\/3637528.3671873","article-title":"\u201cEfficient mixture of experts based on large language models for low-resource data preprocessing., \u201d","volume":"1","author":"Yan","year":"2024","journal-title":"In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"},{"issue":"1","key":"10.1016\/j.procs.2026.01.105_bib18","first-page":"1","article-title":"\u201cMoNet: A Mixture of Experts Solution for Multilingual and Low-Resource ASR Challenges,\u201d","volume":"2","author":"Li","year":"2024","journal-title":"In 2024 International Joint Conference on Neural Networks (IJCNN)"},{"issue":"1","key":"10.1016\/j.procs.2026.01.105_bib19","first-page":"288","article-title":"\u201cMegablocks: Efficient sparse training with mixture-of-experts.,\u201d","volume":"5","author":"Gale","year":"2023","journal-title":"Proceedings of Machine Learning and Systems"},{"issue":"3","key":"10.1016\/j.procs.2026.01.105_bib20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ipm.2025.104078","article-title":"\u201cOvercoming language barriers via machine translation with sparse Mixture-of-Experts fusion of large language models., \u201d","volume":"62","author":"Zhu","year":"2025","journal-title":"Inf Process Manag"},{"issue":"2","key":"10.1016\/j.procs.2026.01.105_bib21","first-page":"34600","article-title":"\u201c On the representation collapse of sparse mixture of experts,\u201d","volume":"1","author":"Chi","year":"2022","journal-title":"Adv Neural Inf Process Syst"},{"issue":"2","key":"10.1016\/j.procs.2026.01.105_bib22","first-page":"524","article-title":"\u201cFsmoe: A flexible and scalable training system for sparse mixture-of-experts models.,\u201d","volume":"1","author":"Pan","year":"2025","journal-title":"In Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems"},{"issue":"2","key":"10.1016\/j.procs.2026.01.105_bib23","doi-asserted-by":"crossref","first-page":"592","DOI":"10.1145\/3718958.3750506","article-title":"\u201cMegaScale-Infer: Efficient Mixture-of-Experts Model Serving with Disaggregated Expert Parallelism.,\u201d","volume":"1","author":"Zhu","year":"2025","journal-title":"In Proceedings of the ACM SIGCOMM 2025 Conference"},{"key":"10.1016\/j.procs.2026.01.105_bib24","doi-asserted-by":"crossref","unstructured":"Maria, A. Z. Abbasi, M. A. Z. Raja, K. S. Nisar, and M. Shoaib, \u201cA novel caputo fractional model for english language learning: Analysis and simulation with bayesian regularization approach,\u201d MethodsX, vol. 14, 2025, doi: 10.1016\/j.mex.2025.103375.","DOI":"10.1016\/j.mex.2025.103375"},{"key":"10.1016\/j.procs.2026.01.105_bib25","unstructured":"Samay Ashar, \u201cLarge Language Models Comparison Dataset,\u201d 2025.https:\/\/www.kaggle.com\/datasets\/samayashar\/large-language-models-comparison-dataset"},{"issue":"6","key":"10.1016\/j.procs.2026.01.105_bib26","doi-asserted-by":"crossref","first-page":"1745","DOI":"10.17507\/tpls.1406.15","article-title":"\u201cPost-Editing a Google Translated Output: Experienced Translators vs. Trainees,\u201d","volume":"14","author":"Khoury","year":"2024","journal-title":"Theory and Practice in Language Studies"},{"issue":"9","key":"10.1016\/j.procs.2026.01.105_bib27","doi-asserted-by":"crossref","first-page":"1568","DOI":"10.1080\/02687038.2024.2320754","article-title":"\u201cValidity and Validation in Language Testing: Current State and Future Guidelines in Aphasiology,\u201d","volume":"38","author":"Marie","year":"2024","journal-title":"Aphasiology"},{"key":"10.1016\/j.procs.2026.01.105_bib28","doi-asserted-by":"crossref","unstructured":"R. Al-Dmour, H. Al-Dmour, and A. Al-Dmour, \u201cThe Crucial Role of EWOM: Mediating the Impact of Marketing Mix Strategies on International Students\u2019 Study Destination Decision,\u201d Sage Open, vol. 14, no. 2, 2024, doi: 10.1177\/21582440241247661.","DOI":"10.1177\/21582440241247661"},{"key":"10.1016\/j.procs.2026.01.105_bib29","first-page":"41829","article-title":"\u201cTransformer-Based Named Entity Recognition in Construction Supply Chain Risk Management in Australia,\u201d in IEEE Access","author":"Shishehgarkhaneh","year":"2024","journal-title":"MONASH University, Department of Civil Engineering, Melbourne, Australia: Institute of Electrical and Electronics Engineers Inc."},{"key":"10.1016\/j.procs.2026.01.105_bib30","doi-asserted-by":"crossref","unstructured":"A. Jaradat and L. Alkhawaja, \u201cA split morphosyntactic analysis of diminutives in two Arabic varieties,\u201d Cogent Arts Humanit, vol. 11, no. 1, 2024, doi: 10.1080\/23311983.2024.2431461.","DOI":"10.1080\/23311983.2024.2431461"},{"issue":"12","key":"10.1016\/j.procs.2026.01.105_bib31","doi-asserted-by":"crossref","first-page":"34219","DOI":"10.1007\/s11042-024-18307-8","article-title":"\u201cA comprehensive literature review on image captioning methods and metrics based on deep learning technique,\u201d","volume":"83","author":"Al-Shamayleh","year":"2024","journal-title":"Multimed Tools Appl"},{"issue":"5","key":"10.1016\/j.procs.2026.01.105_bib32","doi-asserted-by":"crossref","first-page":"1510","DOI":"10.17507\/jltr.1505.12","article-title":"\u201cReflection of Explicitation in Scientific Translation: Neural Machine Translation vs. Human Post-Editing,\u201d","volume":"15","author":"Khoury","year":"2024","journal-title":"Journal of Language Teaching and Research"},{"key":"10.1016\/j.procs.2026.01.105_bib33","doi-asserted-by":"crossref","first-page":"699","DOI":"10.1007\/978-3-031-56586-1_51","article-title":"\u201cThe Effect of Low and High Frequent Term Removal on Documents Clustering,\u201d in Studies in Systems, Decision and Control, vol","author":"Al-Qerem","year":"2024","journal-title":"528, in Studies in systems, decision and control, vol. 528., Cham: Springer Nature Switzerland"},{"issue":"1","key":"10.1016\/j.procs.2026.01.105_bib34","first-page":"109","article-title":"\u201cEfficiency of e-Learning in Applied Materials for Visual Communication Students: An Experimental Study,\u201d","volume":"12","author":"Barakat","year":"2024","journal-title":"International Journal of Society, Culture and Language"},{"issue":"6","key":"10.1016\/j.procs.2026.01.105_bib35","doi-asserted-by":"crossref","first-page":"1854","DOI":"10.17507\/jltr.1506.11","article-title":"\u201cUncovering the Norms of Subtitling Taboo Language Into Arabic: Two and a Half Men From Past to Present,\u201d","volume":"15","author":"Alkhawaja","year":"2024","journal-title":"Journal of Language Teaching and Research"},{"issue":"4","key":"10.1016\/j.procs.2026.01.105_bib36","doi-asserted-by":"crossref","first-page":"231","DOI":"10.5430\/wjel.v14n4p231","article-title":"\u201cContextualizing Canonical Inclusion: The Case of Early Modern English Female-Authored Non-Canonical Verse,\u201d","volume":"14","author":"Al-Shara\u2019h","year":"2024","journal-title":"World Journal of English Language"},{"key":"10.1016\/j.procs.2026.01.105_bib37","doi-asserted-by":"crossref","unstructured":"T. M. Ghazal et al., \u201cGenerative Federated Learning with Small and Large Models In Consumer Electronics for Privacy preserving Data Fusion in Healthcare Internet of Things,\u201d IEEE Transactions on Consumer Electronics, 2025, doi: 10.1109\/TCE.2025.3572629.","DOI":"10.1109\/TCE.2025.3572629"},{"issue":"1","key":"10.1016\/j.procs.2026.01.105_bib38","first-page":"1","article-title":"\u201cDomain Specific Benchmarks for Evaluating Multimodal Large Language Models,\u201d","volume":"2","author":"Anjum","year":"2025","journal-title":"arXiv preprint arXiv:2506.12958."},{"issue":"5","key":"10.1016\/j.procs.2026.01.105_bib39","doi-asserted-by":"crossref","first-page":"1591","DOI":"10.17507\/tpls.1505.24","article-title":"\u201cDesigning Need-Based Learning Material Properly? A Practical Guide for Teachers,\u201d","volume":"15","author":"Al-Shallakh","year":"2025","journal-title":"Theory and Practice in Language Studies"},{"issue":"2","key":"10.1016\/j.procs.2026.01.105_bib40","doi-asserted-by":"crossref","first-page":"1540","DOI":"10.11591\/ijai.v14.i2.pp1540-1547","article-title":"\u201cImproved convolutional neural networks for aircraft type classification in remote sensing images,\u201d","volume":"14","author":"Alraba\u2019nah","year":"2025","journal-title":"IAES International Journal of Artificial Intelligence"},{"key":"10.1016\/j.procs.2026.01.105_bib41","doi-asserted-by":"crossref","unstructured":"M. Elhenawy, H. I. Ashqar, A. Rakotonirainy, T. I. Alhadidi, A. Jaber, and M. A. Tami, \u201cVision-Language Models for Autonomous Driving: CLIP-Based Dynamic Scene Understanding,\u201d Electronics (Switzerland), vol. 14, no. 7, 2025, doi: 10.3390\/electronics14071282.","DOI":"10.3390\/electronics14071282"},{"key":"10.1016\/j.procs.2026.01.105_bib42","doi-asserted-by":"crossref","unstructured":"M. Elhenawy et al., Eyeballing Combinatorial Problems: A Case Study of Using Multimodal Large Language Models to Solve Traveling Salesman Problems, vol. 1268 LNNS. 2024. doi: 10.1007\/978-3-031-82377-0_29.","DOI":"10.1007\/978-3-031-82377-0_29"},{"key":"10.1016\/j.procs.2026.01.105_bib43","doi-asserted-by":"crossref","unstructured":"S. Jaradat, T. I. Alhadidi, H. I. Ashqar, A. Hossain, and M. Elhenawy, \u201cInvestigating patterns of freeway crashes in Jordan: Findings from a text mining approach,\u201d Results in Engineering, vol. 26, 2025, doi: 10.1016\/j.rineng.2025.104413.","DOI":"10.1016\/j.rineng.2025.104413"},{"key":"10.1016\/j.procs.2026.01.105_bib44","doi-asserted-by":"crossref","unstructured":"S. B. Belhaouari and I. Kraidia, \u201cEfficient self-attention with smart pruning for sustainable large language models,\u201d Sci Rep, vol. 15, no. 1, 2025, doi: 10.1038\/s41598-025-92586-5.","DOI":"10.1038\/s41598-025-92586-5"},{"key":"10.1016\/j.procs.2026.01.105_bib45","doi-asserted-by":"crossref","unstructured":"S. Panda et al., \u201cComprehensive framework for smart residential demand side management with electric vehicle integration and advanced optimization techniques,\u201d Sci Rep, vol. 15, no. 1, 2025, doi: 10.1038\/s41598-025-93817-5.","DOI":"10.1038\/s41598-025-93817-5"},{"issue":"2","key":"10.1016\/j.procs.2026.01.105_bib46","doi-asserted-by":"crossref","first-page":"426","DOI":"10.17507\/tpls.1502.12","article-title":"\u201cFreshman Undergraduate Students\u2019 Attitudes Towards Online English Learning: A Case Study at Al-Balqa Applied University,\u201d","volume":"15","author":"Darwish","year":"2025","journal-title":"Theory and Practice in Language Studies"},{"key":"10.1016\/j.procs.2026.01.105_bib47","doi-asserted-by":"crossref","first-page":"19755","DOI":"10.1109\/ACCESS.2025.3534662","article-title":"\u201cAn automatic approach for the identification of offensive language in Perso-Arabic Urdu Language: Dataset Creation and Evaluation,\u201d","volume":"13","author":"Din","year":"2025","journal-title":"IEEE Access"}],"container-title":["Procedia Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1877050926001067?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1877050926001067?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T11:32:11Z","timestamp":1777894331000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1877050926001067"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":47,"alternative-id":["S1877050926001067"],"URL":"https:\/\/doi.org\/10.1016\/j.procs.2026.01.105","relation":{},"ISSN":["1877-0509"],"issn-type":[{"value":"1877-0509","type":"print"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Sparse Mixture-of-Experts Transformers for Efficient Scaling of Large Language Models","name":"articletitle","label":"Article Title"},{"value":"Procedia Computer Science","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.procs.2026.01.105","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}]}}