A small complex-valued recurrent model achieves 100% accuracy on three length-16 state-tracking puzzles, but the claim that state propagation alone is sufficient is not tested against any baseline.
Transformers are rnns: Fast autoregressive transformers with lin- ear attention
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
State Propagation Also Satisfies: A Complex-Valued State-Space Model for Deterministic State Tracking
A small complex-valued recurrent model achieves 100% accuracy on three length-16 state-tracking puzzles, but the claim that state propagation alone is sufficient is not tested against any baseline.