12 papers
PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption
Sahaj Majavdia, Mahdi Taheri
Structured pruning is essential for making neural network inference feasible under homomorphic encryption (HE), yet its impact on model reliability has remained unexplored. This pa…
Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers
Aravind Pradeep, Samira Nazari, Mahdi Taheri +1
Vision Transformers achieve strong image classification accuracy but process all image regions with nearly the same computation, even when many regions are redundant or uninformati…
HASA: Subnet Allocation for Compute-Constrained Model-Heterogeneous Federated Learning
Amir Hossein Shahdadian, Ahmed M. Abdelmoniem, Mahdi Taheri +2
Edge services increasingly use federated learning to personalize on-device models while keeping sensitive data local. In practice, deployments must handle heterogeneity in both cli…
SENTRY: Statistical Reliability Analysis of Vision Transformers Under Soft Errors
Pramit Kumar Bhaduri, Mahdi Taheri, Samira Nazari +3
With the growth of Vision Transformers in safety-critical domains like autonomous systems and medical imaging, ensuring their reliability against soft errors is paramount. While Vi…
Mix-and-Match Pruning: Globally Guided Layer-Wise Sparsification of DNNs
Danial Monachan, Samira Nazari, Mahdi Taheri +4
Deploying deep neural networks (DNNs) on edge devices requires strong compression with minimal accuracy loss. This paper introduces Mix-and-Match Pruning, a globally guided, layer-…
An FPGA-Based SoC Architecture with a RISC-V Controller for Energy-Efficient Temporal-Coding Spiking Neural Networks
Mohammad Javad Sekonji, Ali Mahani, Maryam Mirsadeghi +1
Spiking Neural Networks (SNNs) offer high energy efficiency and event-driven computation, ideal for low-power edge AI. Their hardware implementation on FPGAs, however, faces challe…