---
title: Universal Computing Research
colorFrom: blue
colorTo: indigo
sdk: static
pinned: true
license: apache-2.0
emoji: 🌍
---

<img src="galaxy.png" alt="Background image" width="1200">

# Universal Computing Research

Universal Computing Research is an independent research organization focused on compact language models, efficient architectures, tokenization, and training methods that improve capability under limited compute and parameter budgets.

We release models, code, and experiments for open and reproducible research.

--- 

## Model families

### Limen

Limen is our family of small general-purpose language models.

The first release, **Limen0.2B**, is a 222.5M-parameter base model trained from scratch on 50B tokens. It uses a BoundlessBPE tokenizer that can learn tokens spanning whitespace, along with grouped-query attention and an experimental XSA projection.

[View the Limen model](https://huggingface.co/UniversalComputingResearch/Limen0.2B)

### Atom

Atom is our family of extremely small experimental language models.

These models are used to study compact transformer architectures, custom tokenizers, arithmetic representations, and training curricula at parameter counts below four million.

[View Atom3.4m](https://huggingface.co/UniversalComputingResearch/Atom3.4m) · [View Atom2.7m](https://huggingface.co/UniversalComputingResearch/Atom2.7m)

---

## Research

### Parametrized Random Projection

Parametrized Random Projection replaces dense learned projections with fixed random feature mixing and small learned input and output parameters. The goal is to reduce trainable parameter growth from quadratic to linear while retaining useful projection capacity.

[Read the paper](https://arxiv.org/abs/2512.13480)

---

## Open source

Our models, code, and research artifacts are released for reproducible and practical research.