# Solv3R: 3D Looped Transformer as a Multi-view Solver

Authors: Jeong-gi Kwak, Andrea Tagliasacchi, Sho Kagami, Yuki Ono, Kwang Moo Yi.

Reuses one transformer block to refine a multi-view geometric state. Trains stable, corrective updates so reconstruction can continue when new images arrive, with stopping based on changes in the hidden state.

First public: 2026-11-02.
ArXiv initial submission: 2026-11-02.

[Original paper](https://arxiv.org/abs/2611.02857) · [PDF](https://arxiv.org/pdf/2611.02857) · [HTML](https://arxiv.org/html/2611.02857v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2611.02857/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2611.02857/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2611.02857/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2611.02857/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.