A parameter-reduced CNN detects covert channels in RF receivers at over 90% accuracy on average and runs at 107 GOPs/W on FPGA with minimal accuracy loss.
Edge-first language model inference: Models, metrics, and tradeoffs
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
BaseRT achieves up to 1.56x higher LLM decode throughput than llama.cpp on Apple Silicon through native Metal kernel fusion and unified memory optimizations.
citing papers explorer
-
AI-Enabled Covert Channel Detection in RF Receiver Architectures
A parameter-reduced CNN detects covert channels in RF receivers at over 90% accuracy on average and runs at 107 GOPs/W on FPGA with minimal accuracy loss.
-
BaseRT: Best-in-Class LLM Inference on Apple Silicon via Native Metal
BaseRT achieves up to 1.56x higher LLM decode throughput than llama.cpp on Apple Silicon through native Metal kernel fusion and unified memory optimizations.