mlsanityData to 14 Oct 2026

Unified Implementations of Recurrent Neural Networks in Multiple Deep Learning Frameworks

arXiv 2510.21252 ↗First posted 24 Oct 2025cs.LG cs.SEcited by 0

Not on the map. Why?

Abstract (arXiv)

Recurrent neural networks (RNNs) are a cornerstone of sequence modeling across various scientific and industrial applications. Owing to their versatility, numerous RNN variants have been proposed over the past decade, aiming to improve the modeling of long-term dependencies and to address challenges such as vanishing and exploding gradients. However, no central library is available to test these variations, and reimplementing diverse architectures can be time-consuming and error-prone, limiting reproducibility and exploration. Here, we introduce three open-source libraries in Julia and Python that centralize numerous recurrent cell implementations and higher-level recurrent architectures. torchrecurrent, RecurrentLayers.jl, and LuxRecurrentLayers.jl offer a consistent framework for constructing and extending RNN models, providing built-in mechanisms for customization and experimentation. All packages are available under the MIT license and actively maintained on GitHub.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 39 references that are in the map. First posted on arXiv 24 Oct 2025.

Builds on

23 of 39 references.

References · 23

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  3. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  4. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 669
  5. 2020Time Series Forecasting With Deep Learning: A Surveycited by 459
  6. 2022On the Parameterization and Initialization of Diagonal State Space Modelscited by 424
  7. 2014Deep Speech: Scaling up end-to-end speech recognitioncited by 354
  8. 2015Unitary Evolution Recurrent Neural Networkscited by 294
  9. 2019GRU-ODE-Bayes: Continuous modeling of sporadically-observed time seriescited by 231
  10. 2018Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNNcited by 143
  11. 2019Backpropagation Algorithms and Reservoir Computing in Recurrent Neural Networks for the Forecasting of Complex Spatiotemporal Dynamicscited by 134
  12. 2019AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networkscited by 112
11 more
  1. 2020Learning Long-Term Dependencies in Irregularly-Sampled Time Seriescited by 83
  2. 2020Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependenciescited by 82
  3. 2018Fashionable Modelling with Fluxcited by 53
  4. 2018Light Gated Recurrent Units for Speech Recognitioncited by 48
  5. 2021Long Expressive Memory for Sequence Modelingcited by 41
  6. 2016Minimal Gated Unit for Recurrent Neural Networkscited by 40
  7. 2019FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Networkcited by 38
  8. 2019Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamicscited by 29
  9. 2016Multiplicative LSTM for sequence modellingcited by 27
  10. 2021Working Memory Connections for LSTMcited by 10
  11. 2022ReservoirComputing.jl: An Efficient and Modular Library for Reservoir Computing Modelscited by 8

Built on by

Not cited yet.