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.
A limited memory algo- rithm for bound constrained optimization
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Physically bounded extrapolation models for zero-noise extrapolation reduce unphysical predictions and improve stability compared to unbounded fits on large synthetic benchmarks and real hardware.
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.
-
Improving Zero-Noise Extrapolation via Physically Bounded Models
Physically bounded extrapolation models for zero-noise extrapolation reduce unphysical predictions and improve stability compared to unbounded fits on large synthetic benchmarks and real hardware.