Recurrent Neural Networks

Also known as RNN

Overview

Recurrent neural networks study how a model can process ordered inputs by repeatedly updating an internal state, which is useful for streaming data, long-term memory, and decisions under partial observability. Common approaches include gated LSTMs and GRUs, linear and state-space recurrences, continuous-time and spiking networks, and weight-shared loops for iterative reasoning; training ranges from backpropagation through time to online learning and parallel scans. Researchers test these models on state-tracking and recall tasks, language modeling, time-series forecasting, control, and physical-system prediction. A central tension is how to preserve useful information and stable learning over long sequences while keeping computation efficient and matching the accuracy and flexibility of Transformers.

Latest papers

CardsList

333 papers24 papers in the last four weeks, down 59% on the four weeks before. 0.2% of all new papers.

  1. Learned versus Kinematic Trajectory Prediction under Reduced Observation Frequency

    Nov 17, 2026Nukhbala Gadzhiev, Alexander MorochkoTrajectory PredictionVehicle Trajectory Prediction

  2. BoBDeLaN: Bounded-Bandwidth Context Adaptation for Deep Lagrangian Robot Control

    Nov 16, 2026Lucas Schulze, Sucheth Shenoy, Jan Peters +1Lagrangian Neural NetworksRobust Control

  3. Halting in Recurrent Sequence Models

    Nov 16, 2026Simon DrägerRecurrent Neural NetworksSequence Modeling

  4. Rectified Looped Transformer

    Nov 12, 2026Musheng Li, Jiawei Zhang, Ziyuan Liu +1Recurrent TransformersLanguage Modeling

  5. Quantum Recurrent Architectures for Financial Time Series Prediction

    Nov 11, 2026Danyal Maheshwari, Gerhard Hellstern, Martin Zaefferer +2Time Series ForecastingHybrid Quantum-Classical ML

  6. The Unused Input: The Initial State as a Conditioning Interface for Recurrent TSFMs

    Nov 10, 2026Bernhard Voggenberger, Christian Ganhör, Levente Zólyomi +2Time-Series Foundation ModelsZero-Shot Time Series Forecasting

  7. CURRENT: A Recurrent Neural Network for Concurrent Spatial and Temporal Super-Resolution of 4D Flow MRI

    Nov 10, 2026Luuk Jacobs, Pietro Dirix, Sebastian Kozerke4d flow mriMedical Image Super-Resolution

  8. K-prop: Deep Online Learning by Backpropagating Temporal Kernels

    Nov 9, 2026Bingkun Liu, Paul Haider, Federico Benitez +2Recurrent Neural NetworksTemporal Credit Assignment

  9. Spiking Sensory Networks

    Nov 7, 2026Lleyton AritonSpike-Based Signal EncodingNeural Encoding

  10. MIRA: Mitigating Pole Geometry Bias in Recurrent Language Models

    Nov 6, 2026Róisín Luo, Ihsan Ullah, Christian Gagné +2Recurrent Language ModelsRecurrent Neural Networks

  11. Provable State Estimation with Recurrent Models

    Nov 6, 2026Vincent Andrieu, Pauline Bernard, Lucas Brivadis +2Recurrent Neural NetworksRobot State Estimation

  12. How Finite Brains Generalize Without Bound: Spatial Memory as a Universal Computer

    Nov 5, 2026Yuhang He, Si WuLength GeneralizationRecurrent Neural Networks

  13. Truncated backpropagation through time induces a two-sided gradient turnpike property

    Nov 5, 2026Julian D. Schiller, Matthias A. MüllerTruncated Backpropagation Through TimeRecurrent Neural Networks

  14. Thermally Conditioned Time-Series Forecasting of Grain Growth in Polycrystalline Materials

    Nov 4, 2026Eliane Younes, Elie Hachem, Marc BernackiMaterials ScienceTime Series Forecasting

  15. Attending to Memory Writes Reduces Seed Variability in Recurrent Length Generalization

    Nov 3, 2026Sungwoo Goo, Hwi-yeol Yun, Sangkeun JungRecurrent Neural NetworksLength Generalization

  16. Fault-tolerant shallow recurrent decoders for sparse sensing with missing sensor measurements

    Nov 3, 2026Matteo Romilio Pasqual, Matteo Tomasetto, J. Nathan Kutz +1Learning with Missing DataRecurrent Neural Networks

  17. A theory of noisy linear recurrent neural network learning dynamics

    Oct 26, 2026John J. Vastola, Kanaka RajanRecurrent Neural NetworksNeural Network Training Dynamics

  18. Streaming Recurrent Memory

    Oct 26, 2026Mohamed Elsayed, Minh Pham, A. Rupam MahmoodRecurrent Neural NetworksMemory-Augmented Neural Networks

  19. Leveraging Dale's Principle as an Inductive Bias in Recurrent Neural Networks

    Oct 25, 2026Jiyi Wang, Chenxiao Yang, Yujia Zhao +2Recurrent Neural NetworksNeural Network Stability

  20. Multitask Interactions in Recurrent Dynamics across 100 Cognitive Tasks

    Oct 24, 2026Sílvia García-Hernández, Leema Hamid, Manuel BrennerMulti-Task LearningRecurrent Neural Networks

  21. Data-driven and physics-guided hindcasting of measured wave spectra

    Oct 21, 2026Sander RikkaTime Series ForecastingPhysics-Informed ML

  22. Truncate or Not? A Scaling Study of Looped Transformers with Truncated Backpropagation

    Oct 19, 2026Xuyuan Xiong, Siyu Chen, Zihan Shao +5Truncated Backpropagation Through TimeEfficient Language Model Training

  23. A Spiking Ring-Attractor Architecture for Representation and Control of Revolute Robot Joints

    Oct 19, 2026Aung Htet, Alejandro Rodriguez Jimenez, Ruidong Ma +1Continuous Attractor Neural NetworksRobotic Control

  24. Learning volatility-adaptive forgetting via GARCH-modulated LSTM for stock price forecasting

    Oct 17, 2026Xin-Rui Lu, Da-Qing ZhangStock Price ForecastingTime Series Forecasting

  25. A decomposition-integration framework coupling singular spectrum analysis with a volatility-adaptive LSTM for stock price forecasting

    Oct 17, 2026Xin-Rui Lu, Da-Qing ZhangStock Price ForecastingTime Series Forecasting