From the 1 of 11 linked papers with an AI index.
11 papers
Journey Operators for Structured Multi-Axis Composition
Mahesh Godavarti
The paper introduces a framework for modeling data with structure along multiple axes using journey operators that combine per‑axis transformations, showing when such compositions…
Cumsum-Composable Phase Transport for Low-Cost Streaming Keyword Spotting
Mahesh Godavarti
State-space sequence models are attractive for streaming speech because they maintain compact recurrent state, but scan-style training kernels can have unfavorable constants for sh…
The Context-Ready Transformer
Mahesh Godavarti
We introduce the context-ready transformer, a new recurrent neural network architecture built from a D-layer transformer block that pre-contextualizes each token before it enters t…
Why Do Accumulated Transformations Extrapolate?
Mahesh Godavarti
PaTH Attention showed that replacing RoPE's position-indexed rotations with accumulated data-dependent Householder reflections yields strong length extrapolation, though performanc…
Diversity vs Degrees of Freedom in Gaussian Fading Channels
Mahesh Godavarti
The classical definitions extract degrees of freedom (DOF) via $C(\snr)/\log\snr$ and diversity (DIV) via $-\log P_e(\snr)/\log\snr$, using $\log\snr$ as the common gauge for both.…
Convergence of Differential Entropies -- II
Mahesh Godavarti
We show that under convergence in measure of probability density functions, differential entropy converges whenever the entropy integrands are uniformly integrable…