Author

Yifan Zhang

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

DeepLoop: Depth Scaling for Looped Transformers

The results show that stable recurrent depth requires residual scaling rules that account for parameter visits, not only nominal layer count, and DeepLoop is neutral when no physical block is revisited and improves validation loss and downstream accuracy once recurrent depth is activated.

Shu-zhen Li, Yi-Fan Zhang, Jiacheng Guo et al. · arXiv.org · 2 citations