Comparative Analysis of Liquid Neural Networks and LSTM for Sequential Pattern Recognition: Robustness, Efficiency, and Clinical Utility

A new benchmarking study from arXiv:2605.27467v1 finds that Liquid Neural Networks (LNNs) significantly outperform traditional LSTMs in parameter efficiency and robustness across four sequential data modalities, including clinical time-series and neuromorphic event data. The research demonstrates that LNNs maintain superior performance under temporal dropout stress tests, making them particularly valuable for clinical environments where data sparsity is common.

arXiv:2605.27467v1 Announce Type: new Abstract: Traditional Recurrent Neural Networks RNNs and Long Short-Term Memory LSTM units operate on discrete time steps, often failing to capture the fluid temporal dynamics of real-world physical processes. Liquid Neural Networks LNNs , specifically Closed-form Continuous-time CfC networks, address this by modeling the hidden state evolution as a continuous differential equation. In this paper, we conduct a comprehensive benchmarking study across four distinct sequential modalities: neuromorphic event-based data N-MNIST , stroke-based drawing QuickDraw , visual handwriting IAM , and physiological time-series PhysioNet Sepsis-3 . Furthermore, we perform a rigorous stress test using temporal dropout to evaluate model robustness against missing data. Our findings reveal that LNNs consistently provide superior parameter efficiency and significantly higher robustness in natively temporal domains and clinical environments where data sparsity is prevalent. This extended preprint provides additional background on related datasets and the LNN theoretical lineage, supplemented with a detailed appendix documenting our full implementation and experimental settings.