5 papers
Advancing Model Refinement: Muon-Optimized Distillation and Quantization for LLM Deployment
Jacob Sander, Brian Jalaian, Venkat R. Dasari
Large Language Models (LLMs) enable advanced natural language processing but face deployment challenges on resource-constrained edge devices due to high computational, memory, and…
Neurosymbolic AI Transfer Learning Improves Network Intrusion Detection
Huynh T. T. Tran, Jacob Sander, Achraf Cohen +2
Transfer learning is commonly utilized in various fields such as computer vision, natural language processing, and medical imaging due to its impressive capability to address subta…
Neurosymbolic Artificial Intelligence for Robust Network Intrusion Detection: From Scratch to Transfer Learning
Huynh T. T. Tran, Jacob Sander, Achraf Cohen +2
Network Intrusion Detection Systems (NIDS) play a vital role in protecting digital infrastructures against increasingly sophisticated cyber threats. In this paper, we extend ODXU,…
Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression
Jacob Sander, David Moe, Achraf Cohen +3
Modern foundational models are often compressed via a combination of structured pruning and re-training to meet the strict compute, memory, and connectivity constraints of edge dep…
On Accelerating Edge AI: Optimizing Resource-Constrained Environments
Jacob Sander, Achraf Cohen, Venkat R. Dasari +2
Resource-constrained edge deployments demand AI solutions that balance high performance with stringent compute, memory, and energy limitations. In this survey, we present a compreh…