An end-to-end energy measurement framework for LLM distillation pipelines reveals hidden teacher-side costs and yields selection guidelines plus an open-source harness.
2024.mlco2/codecarbon: v2.4.1
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 6verdicts
UNVERDICTED 6roles
method 1polarities
use method 1representative citing papers
Curates over 900 hours of SRKW acoustic data plus other marine mammal recordings via positive-unlabeled active learning, releasing transformer classifiers that report AUROC 0.58-0.77 and species top-1 accuracy of 53.2% on held-out benchmarks.
Energy-aware metaheuristics use an EI/J score to dynamically pick operators that maximize fitness gain per unit energy, reaching comparable fitness with substantially less energy than standard versions on knapsack, NK-landscapes, and error-correcting code problems.
CTT is a compression pipeline for LLMs that achieves up to 49x memory reduction, 10x faster inference, 81% lower CO2 emissions, and retains 68-98% accuracy on code clone detection, summarization, and generation tasks.
Decentralized ML in IoT networks matches centralized predictive accuracy near 90% but reduces electricity consumption by up to 70% in a railway testbed.
An analytic framework is introduced to estimate memory-related energy costs of AI models and quantify their ecological footprint.
citing papers explorer
-
Towards Resource-Efficient LLMs: End-to-End Energy Accounting of Distillation Pipelines
An end-to-end energy measurement framework for LLM distillation pipelines reveals hidden teacher-side costs and yields selection guidelines plus an open-source harness.
-
Positive-Unlabelled Active Learning to Curate a Dataset for Orca Resident Interpretation
Curates over 900 hours of SRKW acoustic data plus other marine mammal recordings via positive-unlabeled active learning, releasing transformer classifiers that report AUROC 0.58-0.77 and species top-1 accuracy of 53.2% on held-out benchmarks.
-
Energy-Aware Metaheuristics
Energy-aware metaheuristics use an EI/J score to dynamically pick operators that maximize fitness gain per unit energy, reaching comparable fitness with substantially less energy than standard versions on knapsack, NK-landscapes, and error-correcting code problems.
-
Carbon-Taxed Transformers: A Green Compression Pipeline for Overgrown Language Models
CTT is a compression pipeline for LLMs that achieves up to 49x memory reduction, 10x faster inference, 81% lower CO2 emissions, and retains 68-98% accuracy on code clone detection, summarization, and generation tasks.
-
Towards Energy Impact on AI-Powered 6G IoT Networks: Centralized vs. Decentralized
Decentralized ML in IoT networks matches centralized predictive accuracy near 90% but reduces electricity consumption by up to 70% in a railway testbed.
-
Analytic Framework for Estimating Memory Cost
An analytic framework is introduced to estimate memory-related energy costs of AI models and quantify their ecological footprint.