Fast-slow recurrence interleaves quick latent updates with slow observation processing to maintain coherent clustered representations over long horizons, improving out-of-distribution generalization versus LSTM, state space, and Transformer baselines.
Weight Sharing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Thinking While Listening: Fast-Slow Recurrence for Long-Horizon Sequential Modeling
Fast-slow recurrence interleaves quick latent updates with slow observation processing to maintain coherent clustered representations over long horizons, improving out-of-distribution generalization versus LSTM, state space, and Transformer baselines.