Tag
Sigma-Branch restructures pretrained dense networks into a hierarchical binary tree with a shared backbone, routers, and specialized leaves, reducing per-inference active parameters by 58–60% while staying within 1.72 pp of baseline accuracy on CIFAR-100, ImageNet-1K, and ModelNet40.
This paper introduces Program-of-Layers (PoLar), a method that allows LLMs to dynamically skip or loop pretrained layers per input, improving accuracy and efficiency over fixed-depth inference.