# Truncate or Not? A Scaling Study of Looped Transformers with Truncated Backpropagation

> Source: <https://aiflash.com/news/140975/>
> Published: 2026-10-28 07:00:26+00:00

Looped transformers reuse a shared block of layers to increase computational depth without increasing the number of trainable parameters. They are trained with backpropagation through time (BPTT). To save training compute, BPTT is often truncated to the last few loops, but truncation yields biased g