# Loom: A Scalable Analytical Neural Computer Architecture

arXiv: https://arxiv.org/abs/2604.08816 · HTML: https://mlsanity.com/paper/2604.08816/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 23 references that are in the map.
- First posted on arXiv 9 Apr 2026.

## Builds on (most cited first, 17 of 17)

- [Looped Transformers as Programmable Computers](https://mlsanity.com/paper/2301.13196/) (2023)
- [Thinking Like Transformers](https://mlsanity.com/paper/2106.06981/) (2021)
- [Tracr: Compiled Transformers as a Laboratory for Interpretability](https://mlsanity.com/paper/2301.05062/) (2023)
- [On Expressive Power of Looped Transformers: Theoretical Analysis and Enhancement via Timestep Encoding](https://mlsanity.com/paper/2410.01405/) (2024)
- [Simulation of Graph Algorithms with Looped Transformers](https://mlsanity.com/paper/2402.01107/) (2024)
- [Universal Length Generalization with Turing Programs](https://mlsanity.com/paper/2407.03310/) (2024)
- [Looped ReLU MLPs May Be All You Need as Practical Programmable Computers](https://mlsanity.com/paper/2410.09375/) (2024)
- [Constant Bit-size Transformers Are Turing Complete](https://mlsanity.com/paper/2506.12027/) (2025)
- [Autoregressive Large Language Models are Computationally Universal](https://mlsanity.com/paper/2410.03170/) (2024)
- [ALTA: Compiler-Based Analysis of Transformers](https://mlsanity.com/paper/2410.18077/) (2024)
- [Code Simulation as a Proxy for High-order Tasks in Large Language Models](https://mlsanity.com/paper/2502.03568/) (2025)
- [Neural Algorithmic Reasoning for Hypergraphs with Looped Transformers](https://mlsanity.com/paper/2501.10688/) (2025)
- [Learning to Add, Multiply, and Execute Algorithmic Instructions Exactly with Neural Networks](https://mlsanity.com/paper/2502.16763/) (2025)
- [Efficient Turing Machine Simulation with Transformers](https://mlsanity.com/paper/2512.00003/) (2025)
- [Algorithmic Language Models with Neurally Compiled Libraries](https://mlsanity.com/paper/2407.04899/) (2024)
- [Weights to Code: Extracting Interpretable Algorithms from the Discrete Transformer](https://mlsanity.com/paper/2601.05770/) (2026)
- [Transformers are Efficient Compilers, Provably](https://mlsanity.com/paper/2410.14706/) (2024)

## Abstract (arXiv)

We present Loom, a computer architecture that executes programs compiled from C inside a looped transformer whose weights are derived analytically. The architecture implements a 22-opcode instruction set in 8 transformer layers. Each forward pass executes one instruction; the model is applied iteratively until the program counter reaches zero. The full machine state resides in a single tensor X ∈ ℝd × n of fixed size, and every step has fixed cost for fixed d and n, independent of program length or execution history. The default configuration uses d = 155 and n = 1024, yielding 4.7 million parameters and 928 instruction slots. A compact configuration at d = 146 and n = 512 suffices for a 9×9 Sudoku solver (284 instructions). The weights are program-independent: programs live in the state tensor, and the same fixed-weight model executes any compiled program. We make Loom source code publicly available at https://github.com/mkturkcan/Loom.