# Universal Transformers

Authors: Mostafa Dehghani, Stephan Gouws, Oriol Vinyals, Jakob Uszkoreit, Łukasz Kaiser.

Applies recurrence across transformer depth and supports dynamic halting.

First public: 2018-07-10.
ArXiv initial submission: 2018-07-10.

[Original paper](https://arxiv.org/abs/1807.03819) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/1807.03819/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/1807.03819/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/1807.03819/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/1807.03819/record.json)

Summary and categories are editorial. Read the original paper to verify claims and limitations. A citation to a paper does not, by itself, establish that a later method builds on it.

Reading-list version 0.9.5; literature checked through 2026-10-18.