# LoopFold: Parallelizing Recurrent Depth in Looped Transformers

Authors: Feichen Song, Boyi Zeng, Yiqin Hao, Shixiang Song, He Li, Yizhou Yang, Zitong Wang, Yifan Liu, Ziwei He, Zhouhan Lin.

Predicts inputs to later transformer loops so several depths can run in parallel, then corrects their outputs as earlier results arrive. Trains the predictor, corrector and shared backbone together with next-token prediction and measures the accuracy-latency trade-off.

First public: 2026-10-26.
ArXiv initial submission: 2026-10-26.

[Original paper](https://arxiv.org/abs/2610.35556) · [PDF](https://arxiv.org/pdf/2610.35556) · [HTML](https://arxiv.org/html/2610.35556v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2610.35556/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2610.35556/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2610.35556/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2610.35556/record.json)

## Approaches

- [Recurrent reasoning](https://latent-implicit-thinking.github.io/topics/recurrent-reasoning/): Repeat parts of the model or keep intermediate information in memory while working through a problem. Some methods also learn how many passes to run.
- [Alternative generation methods](https://latent-implicit-thinking.github.io/topics/alternative-reasoning-schedules/): Change how intermediate steps are generated, revised, or searched—for example, by refining several steps in parallel. Some produce written chains of thought.

Reading-list version 0.12.0; literature checked through 2026-11-02.