RNNs trained on short ultimately periodic words achieve high out-of-distribution accuracy on most LTL-derived omega-regular language recognition tasks.
4118–4135
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
RNN Generalization to Omega-Regular Languages
RNNs trained on short ultimately periodic words achieve high out-of-distribution accuracy on most LTL-derived omega-regular language recognition tasks.