Recurrent Neural Networks

Also known as RNN

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

303 papers47 papers in the last four weeks, up 15% on the four weeks before. 0.3% of all new papers.

The Computational Value of Sensory-Aligned Receptive Fields Depends on Neuronal Expressivity
Sep 22, 2026Agnese Adorante, Aaron Spieler, Anna LevinaRecurrent Neural Networks Neural Network Expressivity
Department of Computer Science, University of Tübingen, Tübingen, Germany · Max Planck Institute for Biological Cybernetics, Tübingen, Germany
When Recursive Models Finish Computing
Sep 22, 2026Hare Krishna, Shubham Singh, Stephen Ebert +1Sudoku Solving Recurrent Neural Networks
Weinberg Institute, Department of Physics, University of Texas at Austin · Department of Urban and Environmental Policy Planning, Tufts University · Zyphra Technologies, San Francisco, CA, USA +2
PREM: Prefix-Steered Recurrent Memory for Long-Video Understanding
Sep 20, 2026Siru Zhong, Qiongyan Wang, Xiaohui Lv +5Memory-Augmented VLMs Recurrent Neural Networks
The Hong Kong University of Science and Technology (Guangzhou) · Beta Infinity · Tsinghua University
What Can a Recurrent State Safely Forget?
Sep 20, 2026Linzhe Zhang, Changming XuRecurrent Neural Networks Certified Robustness
Graduate School, Northeastern University.
Real-Time Plasma State Prediction via FPGA-Accelerated Quantized Recurrent Probabilistic Neural Networks
Sep 19, 2026Daniel Gaytan-Villarreal, Aiken Xie, Tu Pham +5FPGA-Based Neural Network Acceleration Recurrent Neural Networks
Department of Physics, Carnegie Mellon University, Pittsburgh, PA 15213, USA · Department of Applied Physics and Applied Mathematics, Columbia University, New York, NY 10027, USA · Department of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USA +1
Benchmarking Hybrid Deep Learning Architectures for Predictive Maintenance in Industry 4.0
Sep 18, 2026Zhengyang, Gu, Joseph E. Hernandez +4Hybrid Transformer Architectures Predictive Maintenance
Cissy · Data Science, Liveline Technologies Livonia, MI, USA · Engineering, Liveline Technologies Livonia, MI, USA
Investigating the Performance and Energy Costs of Replicating Band-Split RNN for Music Source Separation
Sep 18, 2026Paul Magron, Romain Serizel, Constance DouwesAudio Source Separation ML Reproducibility
Université de Lorraine, CNRS Inria, LORIA, F-54000 Nancy, France · Centrale Med, Aix Marseille Univ CNRS, LIS, Marseille, France
Recursive Quantum Long Short-Term Memory for Stable Short-Horizon Temperature Forecasting
Sep 17, 2026Mu-En Lee, Yen-Ku Liu, Samuel Yen-Chi Chen +1Time Series Forecasting Quantum Machine Learning
University of Toronto, Toronto, ON, Canada · National Yang Ming Chiao Tung University, Hsinchu, Taiwan · Brookhaven National Laboratory, Upton, NY, USA +1
Learning-Induced Dynamical Transition in Recurrent Neural Networks
Sep 16, 2026Varun VaidyaDynamical Systems Recurrent Neural Networks
Department of Physics, University of South Dakota, Vermillion 57069, USA
RecMorph: Topology-Guided Spatial Recurrence for Generalized Morphology Control
Sep 16, 2026Quanrui Rao, Yong Liu, Xueming Xiao +4Recurrent Neural Networks Cross-Embodiment Robot Learning
Jilin University, China · State Key Laboratory of Special Vehicle Design and Manufacturing Integration Technology, China · Changchun University of Science and Technology, China
Beyond Episodic AI: Cognitive Field Networks for Biologically Inspired Persistent Cognition
Sep 15, 2026Byung Gyu ChaeComputational Cognitive Modeling Recurrent Neural Networks
Electronics and Telecommunications Research Institute, 218 Gajeong-ro, Yuseong-gu, Daejeon 34129, Republic of Korea
Anatomy of Associative Recall in Fixed-State Recurrences: A Matched-State Decomposition, an Interference Wall, and a Curriculum That Breaks It
Sep 14, 2026Julian Boesch, Andrew WeeRecurrent Neural Networks Curriculum Learning
1Purdue University · 2Obit Research
Learned Bow Control on a Measured Bowed-String Model: a Revised Minimum-Bow-Force Law, a Recurrent Controller, and the Domain of a Supervision Ceiling
Sep 14, 2026Homayoon Beigi, Grace ConneelyDynamical Systems Recurrent Neural Networks
Department of Mechanical Engineering, Columbia University, New York, NY, USA · Department of Electrical Engineering, Columbia University, New York, NY, USA · Recognition Technologies, Inc., South Salem, NY, USA
Exploring napping paradigm for Recurrent Spiking Neural Networks
Sep 12, 2026Andreas Massey, Stefano Nichele, Aliaksandr HubinSpiking Neural Networks Recurrent Neural Networks
The Norwegian University of Life Sciences, Elizabeth Stephansens v. 15, 1433 Ås, Norway · Østfold University of Applied Sciences, B R A Veien 4, 1757 Halden, Norway
RunningTensor: Generalizing Linear Attention to Higher-Order Recurrent States
Sep 11, 2026Luca Herranz-Celotti, Vincent GuigueRecurrent Neural Networks Linear Attention
ISIR Sorbonne, France
Temporal Recurrence Favors Fewer Layers
Sep 11, 2026Ivan Anokhin, Johan Obando-Ceron, Irina Rish +1Recurrent Neural Networks Recurrent Language Models
Mila – Qu´ebec AI Institute · Universit´e de Montr´eal · Sakana AI
Thinking with Looped Flows
Sep 10, 2026Ayhan Suleymanzade, Chanhyuk Lee, Floor Eijkelboom +3Test-Time Scaling Recurrent Neural Networks
EPFL · AITHYRA · KAIST +4
Learning Length-Extrapolatable Recurrent Models
Sep 8, 2026Hanwen JiangBackpropagation Temporal Credit Assignment
Adobe Research
Pre-Whitening and BCJR Posterior Distillation for Bi-LSTM Detection in Faster-than-Nyquist Signaling
Sep 7, 2026Nurettin Safak, Osman Tokluoglu, Enver CavusRecurrent Neural Networks
Department of Electrical and Electronics Engineering, Ankara Yildirim Beyazit University, Ankara, Turkiye
Predictive-Coding-Based Autonomous Regulation of Internally Generated and Externally Coupled Processing in Human-Robot Interaction
Sep 7, 2026Henrique Oyama, Hiroki Sawada, Jun TaniPredictive Coding Human-Robot Interaction
Cognitive Neurorobotics Research Unit Okinawa Institute of Science and Technology Graduate University Okinawa
DART: Distributional Adversarial Recurrent Training for Algorithm Learning
Sep 5, 2026Hieu Tran Bao, Phung Thanh Dang, Pham Quang Nhat Minh +1Neural Algorithmic Reasoning Adversarial Training
FPT IS AI R&D Center Hanoi, Vietnam · VNU – University of Engineering and Technology Hanoi, Vietnam
When Quantization Breaks Memory: Recurrent-State Write-Back in Low-Precision Temporal Inference
Sep 3, 2026Ismail Erbas, Xavier Intes, Vikas PandeyRecurrent Neural Networks Recurrent-State Quantization
Department of Biomedical Engineering Center for Modeling, Simulation, and Imaging in Medicine Rensselaer Polytechnic Institute Troy, NY 12180
A Quantum Variational Approach to Prototypical Recurrent Unit
Sep 3, 2026Mahyar Sadeghi Garjan, Tommaso Cesari, Michel BarbeauQuantum Machine Learning Recurrent Neural Networks
School of Electrical Engineering and Computer Science, University of Ottawa, Canada · School of Computer Science, Carleton University, Ottawa, Canada
Modular Deep Recurrent Neural Network: Application to Quadrotors
Sep 3, 2026Nima Mohajerin, Steven L. WaslanderRecurrent Neural Networks Modular Neural Networks
Dept. of Mechanical and Mechatronics Engineering University of Waterloo, Waterloo, ON,Canada
Prospective Coding Improves Learning in Deep Continuous-Time Recurrent Networks
Sep 3, 2026Shivang Rawat, Mirko Morello, Flaviano Morone +1Recurrent Neural Networks Sequence Modeling
Telepath · New York University
Neural-Network Maxent: a general extension with learned nonlinearity, applied to time-series for Desert Locust distribution modelling
Sep 3, 2026Alessandro Grassi, Edoardo Kimani Bellotto, Wassim El Azami +2Gated Recurrent Unit Recurrent Neural Networks
SISTEMA GmbH, Vienna, Austria · Beyond EO, Paris, France
How Temporal Correlations Shape Memory in Linear Recurrent Neural Networks
Aug 31, 2026Arnol Manuel Fokam, Fasseu Sieyondji Akpevwoghene, Edem Fiifi DawsonRecurrent Neural Networks Linear RNNs
Independent Researcher, United Kingdom · Department of Electrical and Electronic Engineering, University of Buea, Cameroon · minoHealth AI Labs, Ghana
"More Is Different'' in Neural Circuits: Algebraic Emergence of Effective Theories in Canonical Recurrent Motifs of Biological Neuronal Networks
Aug 31, 2026Nima DehghaniRecurrent Neural Networks
McGovern Institute for Brain Research, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA · The NSF AI Institute for Artificial Intelligence and Fundamental Interactions (IAIFI), Cambridge, Massachusetts, USAa)
Planning as Dynamics Relaxation: Hippocampal Recurrent Network Realizes Optimal Goal-Directed Navigation
Aug 30, 2026Yuhang He, Junfeng Zuo, Tianhao Chu +1Recurrent Neural Networks
School of Psychological and Cognitive Sciences, Peking University · IDG/McGovern Institute for Brain Research, Peking University · Peking-Tsinghua Center for Life Sciences, Academy for Advanced Interdisciplinary Studies, Peking University +2
Real-Time Monitoring of MHD Liquid Metal Flows with Shallow Recurrent Decoders
Aug 28, 2026Claudio Scardino, Stefano Riva, Carolina Introini +4Magnetohydrodynamics Reduced-Order Modeling
Energy Department, CeSNEF - Nuclear Engineering Division, Politecnico di Milano, Milano · Autodesk Research, 6 Agar Street, London, WC2R 0QE, UK · Argonne National Laboratory, Lemont, IL, 60439, United States of America +1

Sep 22, 2026J/K move · Enter open · S save

The Computational Value of Sensory-Aligned Receptive Fields Depends on Neuronal Expressivity

Agnese Adorante, Aaron Spieler, Anna Levina

Department of Computer Science, University of Tübingen, Tübingen, Germany · Max Planck Institute for Biological Cybernetics, Tübingen, Germany

Recurrent Neural Networks Neural Network Expressivity

Open paper AskPDF arXiv

Biological sensory neurons have selective receptive fields organized along meaningful stimulus coordinates, such as frequency, motion direction, or retinotopic position. Such structure may arise from efficient coding and biological constraints on activity, connectivity, and wiring, as computational studies of simple neurons have shown across modalities. This raises a question: do structured receptive fields confer a computational advantage beyond resource efficiency itself, and does this advantage persist when individual neurons are highly expressive? We address this question in recurrent networks of Expressive Leaky Memory neurons, where we can independently vary neuronal complexity and the organization of feed-forward receptive fields. Across auditory and event-based visual classification tasks, receptive fields aligned with a task-relevant sensory coordinate improve test accuracy relative to budget-matched random receptive fields. This advantage disappears when sensory coordinates are scrambled, or when receptive fields follow task-irrelevant coordinates, showing that the benefit comes from alignment with task geometry rather than restricted connectivity alone. Increasing neuronal complexity reduces the performance advantage of structured receptive fields. Finally, generic synaptic sparsity regularization induces input selectivity and partially recovers performance, but remains substantially below explicitly structured receptive fields, suggesting that sparsity alone is insufficient to recover the full computational benefit of task-aligned receptive fields. Together, our results show that appropriate receptive fields can serve as a computational prior beyond sparsity itself, and that their value depends on the computational expressivity of individual neurons.