The Domain Mixed Unit: A New Neural Arithmetic Layer
Not on the map. Why?
Abstract (arXiv)
The Domain Mixed Unit (DMU) is a new neural arithmetic unit that learns a single parameter gate that mixes between log-space and linear-space representations while performing either addition (DMU add) or subtraction (DMU sub). Two initializations are proposed for the DMU: one covering addition and multiplication, and another covering subtraction and division. The DMU achieves state-of-the-art performance on the NALM Benchmark, a dataset designed to test the ability of neural arithmetic units to generalize arithmetic operations, specifically performing with the highest percentage solved over all seeds on multiplication and division. The DMU will be submitted as a pull request to the open-source NALM benchmark, and its code is available on GitHub at https://github.com/marict/nalm-benchmark
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 6 of its 8 references that are in the map. First posted on arXiv 9 Sep 2025.
Builds on
6 of 8 references.
References · 6
- 2023Llemma: An Open Language Model For Mathematicscited by 388
- 2018Neural Arithmetic Logic Unitscited by 70
- 2020Neural Arithmetic Unitscited by 28
- 2018On Evaluating the Generalization of LSTM Models in Formal Languagescited by 17
- 2021A Primer for Neural Arithmetic Logic Modulescited by 7
- 2019Measuring Arithmetic Extrapolation Performancecited by 4
Built on by
Not cited yet.