Lie Generator Networks learn the generator matrix of post-pulse relaxation dynamics to recover EIS-grade time constants and Nyquist spectra from 60-second data across multiple battery datasets and chemistries.
Interpretable Physics Extraction from Data for Linear Dynamical Systems using Lie Generator Networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Attention decomposes into low-rank routing and symmetric filtering; disentangled S-D attention reveals a spectral cascade allowing early-layer linearization at under 5% perplexity cost.
citing papers explorer
-
Lie Generator Networks Extract EIS-Grade Battery Diagnostics from Pulse Relaxation Data
Lie Generator Networks learn the generator matrix of post-pulse relaxation dynamics to recover EIS-grade time constants and Nyquist spectra from 60-second data across multiple battery datasets and chemistries.
-
The Routing and Filtering Structure of Attention
Attention decomposes into low-rank routing and symmetric filtering; disentangled S-D attention reveals a spectral cascade allowing early-layer linearization at under 5% perplexity cost.