{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T20:50:43Z","timestamp":1776977443058,"version":"3.51.4"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T00:00:00Z","timestamp":1751500800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T00:00:00Z","timestamp":1751500800000},"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":[[2025,7,3]]},"DOI":"10.1109\/icecet63943.2025.11472481","type":"proceedings-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T19:42:35Z","timestamp":1775763755000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Energy-Aware LLMs: A step towards sustainable AI for downstream applications"],"prefix":"10.1109","author":[{"given":"Nguyen Phuc","family":"Tran","sequence":"first","affiliation":[{"name":"Concordia University,Computer Science and Software Engineering,Montréal,Canada"}]},{"given":"Brigitte","family":"Jaumard","sequence":"additional","affiliation":[{"name":"Concordia University,Computer Science and Software Engineering,Montréal,Canada"}]},{"given":"Oscar","family":"Delgado","sequence":"additional","affiliation":[{"name":"École de Technologie Supérieure,Systems Engineering,Montréal,Canada"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3639856.3639892"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629553"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/COMSNETS59351.2024.10427044"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651329"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2300473"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00071"},{"key":"ref7","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Int. Conference on Learning Representations","author":"Hu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2024.3350661"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3005348"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3334614"},{"key":"ref11","first-page":"10323","article-title":"Sparsegpt: Massive language models can be accurately pruned in one-shot","volume-title":"Int. Conference on Machine Learning","author":"Frantar"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.587"},{"key":"ref13","first-page":"699","article-title":"Quant-LLM: Accelerating the Serving of Large Language Models via FP6-Centric Algorithm-System Co-Design on Modern GPUs","volume-title":"USENIX Annual Technical Conference (USENIX ATC 24)","author":"Xia"},{"key":"ref14","article-title":"A simple and effective pruning approach for large language models","volume-title":"Workshop on Efficient Systems for Foundation Models@ ICML2023","author":"Sun"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.sustainlp-1.2"},{"key":"ref16","article-title":"BERTScore: Evaluating Text Generation with BERT","volume-title":"Int. Conference on Learning Representations (ICLR)","author":"Zhang"},{"key":"ref17","first-page":"65","article-title":"METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments","volume-title":"ACL workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref19","first-page":"74","article-title":"ROUGE: A Package for Automatic Evaluation of Summaries","volume-title":"Text summarization branches out","author":"Lin","year":"2004"},{"key":"ref20","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"Meta"},{"key":"ref21","article-title":"Gemma: Open models based on gemini research and technology","author":"Mesnard","year":"2024","journal-title":"Google Deep Mind"},{"key":"ref22","first-page":"196","article-title":"Atom: Low-bit quantization for efficient and accurate llm serving","volume-title":"Proceedings of Machine Learning and Systems","volume":"6","author":"Zhao"}],"event":{"name":"2025 5th International Conference on Electrical, Computer and Energy Technologies (ICECET)","location":"Paris, France","start":{"date-parts":[[2025,7,3]]},"end":{"date-parts":[[2025,7,6]]}},"container-title":["2025 5th International Conference on Electrical, Computer and Energy Technologies (ICECET)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11471878\/11471697\/11472481.pdf?arnumber=11472481","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T19:57:03Z","timestamp":1776974223000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11472481\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,3]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icecet63943.2025.11472481","relation":{},"subject":[],"published":{"date-parts":[[2025,7,3]]}}}