Quantization

Weight Pair Encoding (WeightPE): Inducing a Smaller Grammar in Neural Network Weights

權重配對編碼（WeightPE）：將類神經網路權重壓縮為更小、更具彈性的語法結構

This study introduces WeightPE, the first method to use grammar size as an explicit training objective, optimizing neural network weights into highly compressible, hierarchical, and variable-length structures.