Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications

ArXi:2605.11855v1 Announce Type: cross Sequence learning is dominated by Transformers and parallelizable recurrent neural networks (RNNs) such as state-space models, yet learning long-term dependencies remains challenging, and state-of-the-art designs trade power consumption for performance. The Bistable Memory Recurrent Unit (BMRU) was