Partial Answer of How Transformers Learn Automata

We introduce a novel framework for simulating finite automata using representation-theoretic semidirect products and Fourier modules, achieving more efficient Transformer-based implementations.

@article{tiantian2025_2504.20395,
  title={ Partial Answer of How Transformers Learn Automata },
  author={ Tiantian and Zhang },
  journal={arXiv preprint arXiv:2504.20395},
  year={ 2025 }
}