5 papers
StepCache: Step-Level Reuse with Lightweight Verification and Selective Patching for LLM Serving
Azam Nouri
We address LLM serving workloads where repeated requests share a common solution structure but differ in localized constraints, such as output schema, variable names, or numeric co…
Significance-Gain Pair Encoding for LLMs: A Statistical Alternative to Frequency-Based Subword Merging
Azam Nouri
Subword tokenization is a key design choice for modern language models, including large language models (LLMs), with byte- and character-level BPE serving as a widely used baseline…
Critical Exponent Elliptic Equations on the Half-Space: Uniqueness and Explicit Solutions
Azam Nouri
We prove that all positive solutions of on the upper half space (for ) satisfying the boundary condition $D_{x_n}u = -u^{\f…
A Sobel-Gradient MLP Baseline for Handwritten Character Recognition
Azam Nouri
We revisit the classical Sobel operator to ask a simple question: Are first-order edge maps sufficient to drive an all-dense multilayer perceptron (MLP) for handwritten character r…
An MLP Baseline for Handwriting Recognition Using Planar Curvature and Gradient Orientation
Azam Nouri
This study investigates whether second-order geometric cues - planar curvature magnitude, curvature sign, and gradient orientation - are sufficient on their own to drive a multilay…