| --- |
| license: mit |
| pipeline_tag: text-generation |
| --- |
| |
| # Solve the Loop: Attractor Models for Language and Reasoning |
|
|
| Attractor Models are a family of models that use a backbone module to propose output embeddings, followed by an attractor module that refines them by solving for a fixed point using implicit differentiation. This architecture allows for iterative refinement with constant training memory and adaptive inference-time computation. |
|
|
| [**Project Page**](https://attractor-models.github.io/) | [**Paper (arXiv:2605.12466)**](https://arxiv.org/abs/2605.12466) | [**GitHub**](https://github.com/jacobfa/Attractor) |
|
|
| ## Introduction |
| Attractor Models offer a promising alternative to feed-forward computation by iteratively refining latent representations. In language modeling, Attractor Models deliver a Pareto improvement over standard Transformers, improving perplexity and downstream accuracy while reducing training cost. This repository contains the **Attractor-370M** model. |
|
|
| ## Sample Usage |
|
|
| To use this model, you need to install the `attractor` package from the [official repository](https://github.com/jacobfa/Attractor): |
|
|
| ```bash |
| git clone https://github.com/jacobfa/Attractor |
| cd Attractor |
| pip install -e . |
| ``` |
|
|
| Then, you can construct the model in Python: |
|
|
| ```python |
| from attractor.models.attractor import Attractor, AttractorConfig |
| |
| # Loading the configuration for the 370M model |
| config = AttractorConfig.from_name("attractor-medium-370m") |
| model = config.construct_model() |
| ``` |
|
|
| ## Citation |
|
|
| ```bibtex |
| @article{feinashley2026attractor, |
| title={Solve the Loop: Attractor Models for Language and Reasoning}, |
| author={Fein-Ashley, Jacob and Rashidinejad, Paria}, |
| year={2026}, |
| url={https://arxiv.org/abs/2605.12466} |
| } |
| ``` |
