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.

Mechanical Field Networks: Structured Neural Dynamics for Multivariate Systems
Jun 8, 2026Xingji CuiMultivariate Time Series Forecasting Dynamical Systems
Xi’an Jiaotong University, China
Backward Coherence and Hidden-State Stability in Recurrent Neural Networks: A Quasi-Reverse-Martingale Theory
Jun 8, 2026Yuan-chin Ivan ChangRecurrent Neural Networks Neural Network Stability
Institute of Statistical Science, Academia Sinica · Academia Road, Section 2, Nankang, Taipei 115, Taiwan
A Held-Out Transition-Pair Falsifier for Long-Horizon Non-Abelian State Tracking
Jun 5, 2026Jeonghoon LeeRecurrent Neural Networks State Tracking
Attractor Dynamics
Product units in gated recurrent units improve nuclear-mass prediction
Jun 5, 2026Ziyuan Li, Paulo S. A. Freitas, John W. Clark +1Recurrent Neural Networks Complex-Valued Neural Networks
Department of Mathematics, Informatics and Technology, University of Applied Sciences Koblenz, Joseph-Rovan-Allee 2, 53424 Remagen, Germany · Technical University of Munich, Munich, Germany · Department of Mathematics, University of Madeira, Campus Universitário da Penteada, Funchal, 9020-105, Portugal +1
Pretraining Recurrent Networks without Recurrence
Jun 4, 2026Akarsh Kumar, Phillip IsolaRecurrent Neural Networks Predictive State Representations
MIT
Field Validation of a Multi-Resolution ConvLSTM Framework for Retaining Wall Deformation Prediction
Jun 4, 2026Jihoon Kim, Saeyon Kim, Heejung YounRecurrent Neural Networks Spatiotemporal Forecasting
Department of Civil and Environmental Engineering, Hongik University, Seoul 04066, Republic of Korea
Seq103: A Unified Neuroevolution Framework for Compact Sequence Architecture Discovery
Jun 3, 2026Wenxiao Li, Yongjian Liu, Qing XieEvolutionary Optimization Time Series Classification
School of Computer Science and Artificial Intelligence, Wuhan University of Technology, No. 122 Luoshi Road, Hongshan District, Wuhan, 430070, Hubei, China
Physics-Guided Recurrent State-Space Neural Networks for Multi-Step Prediction
Jun 1, 2026Ruiyuan Li, Ajay Seth, Manon KokTime Series Forecasting Recurrent Neural Networks
Delft Center for Systems and Control, TU Delft, the Netherlands · Department of Biomechanical Engineering, TU Delft, the Netherlands
An Algebraic View of the Expressivity of Recurrent Language Models
Jun 1, 2026Franz Nowak, Ryan Cotterell, Reda BoumasmoudRecurrent Neural Networks Neural Network Expressivity
ETHZürich.
CART: Context-Anchored Recurrent Transformer -- A Parameter-Efficient Architecture with Learned Stability
May 31, 2026Chad A. CappsRecurrent Neural Networks Autoregressive Language Modeling
Independent Researcher
Tiny Recursive Models for Solving the J2-Perturbed Lambert Problem
May 30, 2026Minduli Wijayatunga, Roberto ArmellinDynamical Systems Trajectory Optimization
Department of Aerospace Engineering University of Illinois Urbana-Champaign Urbana-Champaign, IL, USA · Te Pūnaha Ātea – Space Institute University of Auckland Auckland, New Zealand
Dynamics and Representation Structure of Local Approximations to Gradient-Based Learning in Linear Recurrent Neural Networks
May 29, 2026Ezekiel Williams, Alexandre Payeur, Guillaume LajoieTruncated Backpropagation Through Time Recurrent Neural Networks
Department of Mathematics and Statistics, Universit´e de Montr´eal, Canada · Mila Qu´ebec, Canada · Imperial College London, United Kingdom
Neuro-symbolic Syntactic Parsing: Shaping a Neural Network with the CYK Algorithm
May 29, 2026Fabio Massimo Zanzotto, Federico Ranaldi, Giorgio SattaNeural Algorithmic Reasoning Recurrent Neural Networks
Human-centric ART, University of Rome Tor Vergata, Italy · DEI, University of Padua, Italy
Why Linear Recurrent Memory Works in Partially Observable Reinforcement Learning
May 29, 2026Yike Zhao, Onno Eberhard, Malek Khammassi +2Partially Observable RL Markov Models
EPFL, Lausanne, Switzerland · Max Planck Institute for Intelligent Systems, Tübingen, Germany
Memory by Design: Bayesian Layers for Sequence Modeling
May 29, 2026Matthew Dowling, Hyungju Jeon, Cristina Savin +1Long-Context Retrieval Bayesian Filtering
Champalimaud Research, Champalimaud Foundation, Portugal · Center for Neural Science, New York University, USA · Center for Data Science, New York University, USA
Chess-World-Model: A 10M-Game Benchmark for Exact State Tracking from Chess Move Sequences
May 28, 2026Benjamin Walker, Terry LyonsRecurrent Neural Networks State Tracking
Mathematical Institute, University of Oxford · Department of Mathematics, Imperial College London
Enhancing BiGRU with a KAN Block for Legal Document Classification and Summarization
May 27, 2026Ahmed Faizul Haque Dhrubo, Souvik Pramanik, Most. Aysha Siddika Sumona +4Recurrent Neural Networks Text Summarization
Dept. of ECE North South University, Dhaka, Bangladesh
Learning Compositional Latent Structure with Vector Networks
May 27, 2026Niclas Pokel, Benjamin F. GreweRepresentation Learning Recurrent Neural Networks
Institute of Neuroinformatics, UZH / ETH Zurich ETH AI Center Zurich, Switzerland
Length Generalization with Log-Depth Recurrent Units
May 25, 2026Charles Pert, Dalal Alrajeh, Alessandra RussoRecurrent Neural Networks Length Generalization
Department of Computing Imperial College London
Growing a Neural Network in Breadth, Depth, and Time
May 24, 2026Eivinas Butkus, Kedar Garzón Gupta, Nikolaus KriegeskorteRecurrent Neural Networks Dynamic Neural Networks
1Columbia University · 2NSF AI Institute for Artificial and Natural Intelligence
Streaming Reinforcement Learning under Partial Observability with Real-Time Recurrent Learning
May 23, 2026Noah Farr, Aryaman Reddi, Carlo D'Eramo +1Reinforcement Learning Partially Observable RL
Technical University of Darmstadt · Zuse School ELIZA · Center for Artificial Intelligence and Data Science, University of Würzburg +1
On the Stability and Realizability of Recurrent Polynomial Surrogate Ternary Logic Gate Networks
May 23, 2026Sai Sandeep Damera, Ryan Matheu, Aniruddh G. Puranic +2Logical Reasoning Signal Temporal Logic
University of Maryland, College Park, USA
Memory Uncertainty Relation and Harmonic Memory in Random Recurrent Networks
May 23, 2026Taichi Haruna, Kohei NakajimaRecurrent Neural Networks Reservoir Computing
Department of Information and Mathematical Sciences, School of Arts and Sciences, Tokyo Woman’s Christian University, 2-6-1 Zempukuji, Suginami-ku, Tokyo 167-8585, Japan · Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo 113-8656, Japan
LC-Flow: Learning Local Continuous Optical Flow and Confidence from events
May 23, 2026Gunwoo Jeon, Chaesong Park, Jongwoo LimOptical Flow Event-Based Vision
IPAI, Seoul National University
Multi-Fidelity Learning with Shallow Recurrent Decoders for Reactor Physics
May 22, 2026Stefano Riva, Carolina Introini, J. Nathan Kutz +1Neural Surrogate Modeling Recurrent Neural Networks
Autodesk Research, London, UK · Department of Energy, Nuclear Engineering Division, Politecnico di Milano, Milan, Italy · Department of Mechanical and Nuclear Engineering and Emirates Nuclear Technology Center, Khalifa University, Abu Dhabi (127788), United Arab Emirates
HRM-Text: Efficient Pretraining Beyond Scaling
May 20, 2026Guan Wang, Changling Liu, Chenyu Wang +6Language Model Pretraining Recurrent Neural Networks
1Sapient Intelligence · 2MIT
CogScale: Scalable Benchmark for Sequence Processing
May 19, 2026Yannis Bendi-Ouis, Romain de Coudenhove, Xavier HinautRecurrent Neural Networks Synthetic Benchmark Generation
Mnemosyne · Mnemosyne Inria Bordeaux, France · ENS-PSL +1
An Objective Performance Evaluation of the LSTM Networks in Time Series Classification
May 19, 2026Sooraj Sunil, Balakumar BalasingamTime Series Classification Recurrent Neural Networks
Electrical and Computer Engineering University of Windsor Windsor, ON, Canada
Learned Memory Attenuation in Sage-Husa Kalman Filters for Robust UAV State Estimation
May 18, 2026Kenan Majewski, Marcin ŻugajKalman Filtering UAV Navigation
Institute of Aeronautics and Applied Mechanics, Warsaw University of Technology, Nowowiejska 24, Warsaw, 00-665, Poland
Sequential Structure in Intraday Futures Data: LSTM vs Gradient Boosting on MNQ
May 18, 2026Mathias MesfinGradient-Boosted Decision Trees Quantitative Finance
Independent Researcher

Jun 8, 2026J/K move · Enter open · S save

Mechanical Field Networks: Structured Neural Dynamics for Multivariate Systems

Xingji Cui

Xi’an Jiaotong University, China

Multivariate Time Series Forecasting Dynamical Systems Latent Dynamics Modeling Nonlinear System Identification Recurrent Neural Networks

Open paper AskPDF arXiv

Many multivariate dynamical systems are observed only through trajectories, leaving the mechanisms governing their joint dynamics hidden. Existing approaches can impose interpretable dynamics or learn flexible state transitions, yet the resulting interaction structure is typically either specified in advance or left implicit within the learned dynamics. We introduce MF-Net, a recurrent dynamical model that represents all variables in a shared field state and updates this state through a learned relation law. Each variable carries a field component, and these components evolve jointly through a learnable mechanical transition. Here, mechanical refers to the relation-to-motion organization of the transition, where learned relations shape state-dependent flows, field responses, and motion tendencies that move the field state forward. The resulting structure is part of the rollout itself: learned relations influence how the field moves, and the same internal quantities support both forecasting and structural readout. Across known-law interaction systems, chaotic benchmarks, real neural recordings, and ecological time series, MF-Net achieves competitive short- and medium-horizon forecasting while retaining inspectable structural readout. On the 40-dimensional Lorenz--96 testbed, MF-Net achieves an eight-step

R^2

0.798\pm0.018

; across five seeds, its learned relation matrix recovers the local coupling support with a local/nonlocal strength ratio of

19.80\pm1.00

and Precision@

K

1.000\pm0.000

. MF-Net provides a structure-readable dynamical modeling framework in which learned relations are trained through forward evolution and, on real data, interpreted as functional predictive couplings under appropriate observational limits.