Abstract: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 $X \in \mathbb{R}^{d \times n}$ 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$\times$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 this https URL.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2604.08816 [cs.LG] |
| (or arXiv:2604.08816v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2604.08816 arXiv-issued DOI via DataCite |
From: Mehmet Kerem Turkcan [view email]
[v1]
Thu, 9 Apr 2026 23:11:28 UTC (19 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。