AI RESEARCH

HGQ-LUT: Fast LUT-Aware Training and Efficient Architectures for DNN Inference

arXiv CS.LG

ArXi:2604.22293v1 Announce Type: cross Lookup-table (LUT) based neural networks can deliver ultra-low latency and excellent hardware efficiency on FPGAs by mapping arithmetic operations directly onto the logic primitives. However, state-of-the-art LUT-aware