# LoopVQ: Sub 1-bit KV Cache Quantization for Looped Transformers

Authors: Minsoo Cheong, Sungjoo Yoo.

Compresses related key–value cache entries across loops with shared vector codes, then adjusts the codebooks to match the original model’s outputs. Implements the compressed cache in a serving system.

First public: 2026-11-03.
ArXiv initial submission: 2026-11-03.

[Original paper](https://arxiv.org/abs/2611.05304) · [PDF](https://arxiv.org/pdf/2611.05304) · [HTML](https://arxiv.org/html/2611.05304v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2611.05304/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2611.05304/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2611.05304/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2611.05304/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.

Reading-list version 0.15.2; literature checked through 2026-11-03.