Domain-specialized small language models enable deterministic atomic-resolution scanning probe microscopy control with 99.3% command accuracy, lower computational cost, and better domain performance than larger general models.
From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference,
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
Execution-idle accounts for 19.7% of GPU execution time and 10.7% of energy in a large cluster, motivating power management that treats it as a distinct operating state.
LLM inference should be reframed and evaluated as energy-to-token production with a Token Production Function that accounts for power, cooling, and efficiency ceilings.
MADP multi-agent pipeline with human-in-the-loop achieves 97% full automation on 955 real documents, 98.5% accuracy on ablation set, and 69-70% reductions in FTE, energy, and emissions versus manual processing.
G-TRACE provides region-aware estimates of GenAI carbon emissions including 4309 MWh and 2068 tCO2 for a 2024-2025 image generation trend, paired with a seven-level AI Sustainability Pyramid for policy guidance.
A systematic review finds research on the sustainability of LLM-generated code to be limited, fragmented, and without accepted frameworks for measurement or benchmarking.
Empirical comparison shows smaller open-weight LLMs achieve strong performance on everyday work tasks, supporting task-aware selection over always using the largest models for sustainability and cost reasons.
citing papers explorer
-
Integrating Domain-Specialized Language Models with AI Measurement Tools for Deterministic Atomic-Resolution Experimentation
Domain-specialized small language models enable deterministic atomic-resolution scanning probe microscopy control with 99.3% command accuracy, lower computational cost, and better domain performance than larger general models.
-
The Energy Cost of Execution-Idle in GPU Clusters
Execution-idle accounts for 19.7% of GPU execution time and 10.7% of energy in a large cluster, motivating power management that treats it as a distinct operating state.
-
Position: LLM Inference Should Be Evaluated as Energy-to-Token Production
LLM inference should be reframed and evaluated as energy-to-token production with a Token Production Function that accounts for power, cooling, and efficiency ceilings.
-
MADP: A Multi-Agent Pipeline for Sustainable Document Processing with Human-in-the-Loop
MADP multi-agent pipeline with human-in-the-loop achieves 97% full automation on 955 real documents, 98.5% accuracy on ablation set, and 69-70% reductions in FTE, energy, and emissions versus manual processing.
-
Quantifying the Climate Risk of Generative AI: Region-Aware Carbon Accounting with G-TRACE and the AI Sustainability Pyramid
G-TRACE provides region-aware estimates of GenAI carbon emissions including 4309 MWh and 2068 tCO2 for a 2024-2025 image generation trend, paired with a seven-level AI Sustainability Pyramid for policy guidance.
-
Sustainable Code Generation Using Large Language Models: A Systematic Literature Review
A systematic review finds research on the sustainability of LLM-generated code to be limited, fragmented, and without accepted frameworks for measurement or benchmarking.
-
Sustainability via LLM Right-sizing
Empirical comparison shows smaller open-weight LLMs achieve strong performance on everyday work tasks, supporting task-aware selection over always using the largest models for sustainability and cost reasons.