Probability Distributions Computed by Hard-Attention Transformers.

Andy Yang Anej Svete Jiaoda Li Anthony Widjaja Lin Jonathan Rawski Ryan Cotterell David Chiang 0001 Probability Distributions Computed by Hard-Attention Transformers. 2025 October abs/2510.27118 CoRR https://doi.org/10.48550/arXiv.2510.27118 db/journals/corr/corr2510.html#abs-2510-27118 streams/journals/corr