EnergyLens derives a twelve-parameter closed-form energy model via symbolic regression that achieves 88.2% top-1 configuration accuracy with 50 samples and extrapolates to unseen batch sizes and hardware.
Greedy function approximation: A gradient boosting machine
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A reliability-aware framework for ETF tail-risk monitoring integrates service-time quality checks, lower-tail predictions, uncertainty scoring, and adjustments, showing empirical improvements especially during stressed periods and under simulated data degradation.
citing papers explorer
-
EnergyLens: Interpretable Closed-Form Energy Models for Multimodal LLM Inference Serving
EnergyLens derives a twelve-parameter closed-form energy model via symbolic regression that achieves 88.2% top-1 configuration accuracy with 50 samples and extrapolates to unseen batch sizes and hardware.
-
Reliability-Aware ETF Tail-Risk Monitoring
A reliability-aware framework for ETF tail-risk monitoring integrates service-time quality checks, lower-tail predictions, uncertainty scoring, and adjustments, showing empirical improvements especially during stressed periods and under simulated data degradation.