Poster Type: Research Posters
Author: Sadegh Jafari (Iowa State University), Mohiuddin Bilwal (Iowa State University), Fan Zhou (Iowa State University), Brian Gelder (Iowa State University), Ali Jannesari (Iowa State University)
Abstract: Deep neural networks are powerful but too large to run cheaply on edge devices. Pruning and quantization help, but deciding how and where to compress a model is still manual, or relies on algorithms that are hard to apply across architectures. We introduce APQF, an agentic profiling-guided framework that combines structured pruning, mixed-precision quantization-aware training, and accuracy recovery in one automated pipeline. A profiling agent measures cost distribution and pruning sensitivity, which then drive per-group pruning ratios, per-layer bit-widths, and the recovery strategy. Our experiments on ImageNet and CIFAR-10 show that APQF compresses convolutional and transformer models further than a joint pruning and quantization baseline at comparable or higher accuracy, and stays stable across different planners, including free open-weight ones.
Best Poster Finalist (BP): no
Poster: PDF
Poster Summary: PDF