works on

From the 1 of 11 linked papers with an AI index.

collaborators

11 papers

cs.LG2026

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…

cs.SD2026

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…

cs.CL2026

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…

cs.LG2026

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…

cs.IT2026

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.…

cs.IT2026

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…