works on
depth scaling 1language models 1looped architecture 1residual scaling 1transformers 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.LG2026

DeepLoop: Depth Scaling for Looped Transformers

Shuzhen Li, Yifan Zhang, Jiacheng Guo +2

DeepLoop reuses a compact stack of transformer blocks across multiple passes to increase model depth without adding parameters, and introduces new residual scaling rules to keep tr…