Gated Recurrent Transformers: 3-layer recurrent model matches 12-layer GPT-2 with 63% fewer params

burny_tech · x · 2026-09-20

Researchers introduce the Gated Recurrent Transformer (GRT), a recurrent-depth architecture that brackets a single shared core block with fixed prelude and coda modules, iterating the core R times. Inspired by gated RNNs, a lightweight projection and an elementwise update gate — conditioned on the hidden state, the prelude output, and per-step resampled noise — modulate the recurrent update, letting a few shared layers achieve the functional diversity that normally requires many unique layers.

Key results:

Paper: arXiv:2608.15062, by Amr Hegazy, Amr Alanwar, Mostafa Elhoushi.

Original post →

More from Research

Research channel →