A transformer trained on random meaningless MicroPy programs generalizes to execute diverse human-written programs, providing empirical evidence it can act as a universal computer.
Position coupling: Improving length generalization of arithmetic transformers using task structure
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 2polarities
background 2representative citing papers
Parameter reconstruction algorithm for SNN training obtained by extending convexification of parallel feedforward threshold networks to the recurrent case that subsumes SNNs.
citing papers explorer
-
Training Transformers as a Universal Computer
A transformer trained on random meaningless MicroPy programs generalizes to execute diverse human-written programs, providing empirical evidence it can act as a universal computer.
-
Globally Optimal Training of Spiking Neural Networks via Parameter Reconstruction
Parameter reconstruction algorithm for SNN training obtained by extending convexification of parallel feedforward threshold networks to the recurrent case that subsumes SNNs.