2 papers
cs.LG2026
Scaling Laws in the Tiny Regime: How Small Models Change Their Mistakes
Mohammed Alnemari, Rizwan Qureshi, Nader Begrazadah
Neural scaling laws describe how model performance improves as a power law with size, but existing work focuses on models above 100M parameters. The sub-20M regime -- where TinyML…
cs.CV2025
Equivariant-Aware Structured Pruning for Efficient Edge Deployment: A Comprehensive Framework with Adaptive Fine-Tuning
Mohammed Alnemari
This paper presents a novel framework combining group equivariant convolutional neural networks (G-CNNs) with equivariant-aware structured pruning to produce compact, transformatio…