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.

Scalable Multi-GPU Simulation of 3D Multicellular Growth with RNN-Based Workload Balancing
Aug 26, 2026Matvey Moisseyev, Huijing Du, Dandan Zheng +2Domain Decomposition Methods Recurrent Neural Networks
School of Computing, University of Nebraska–Lincoln · Department of Mathematics, University of Nebraska–Lincoln · Department of Radiation Oncology, University of Rochester Medical Center +2
Steering Recurrent Reasoners at Inference Time with Readout Feedback
Aug 25, 2026Shunsuke Kamiya, Masanori Koyama, Seongcheol Jeong +5Inference-Time Guidance Recurrent Neural Networks
Graduate School of Engineering, The University of Tokyo
Free-Energy-Gated Plasticity for Real-Time Online Motor Learning in Physical Human-Robot Interaction
Aug 24, 2026Hiroki Sawada, Jun TaniOnline Continual Learning Continual Robot Learning
Cognitive Neurorobotics Research Unit, Okinawa Institute of Science and Technology Graduate University, Okinawa, Japan 904-0302
SANE: State Anomaly Neutralization for Stable Extreme-Context Delta-Rule Models
Aug 23, 2026Qingwen Lin, Boyan Xu, Xiao Liu +2Recurrent Neural Networks Gated Delta Networks
School of Computer Science, Guangdong University of Technology · Yuanshi Intelligence · College of Science, Shantou University
DevGRU: Depth-guided Visual Navigation using a Collision-aware Recurrent Model
Aug 19, 2026Kyung Min Han, Eunsom Kim, Young J. KimGated Recurrent Unit Robot Navigation
Think Shallow, Solve Deep: Controlling Recurrent Dynamics for Reliable Test-Time Depth
Aug 18, 2026Ivan Viakhirev, Kirill Borodin, Amirah Almutairi +3Test-Time Scaling Recurrent Neural Networks
FRC RAS, Saint-Petersburg, Russia · ITMO, Saint-Petersburg, Russia · lab260, Moscow, Russia +4
Dynamic Compression in Recurrent Networks
Aug 18, 2026Jyothish Pari, Ryan Bahlous-Boldi, Pulkit AgrawalRecurrent Neural Networks Model Compression
Improbable AI Lab, Massachusetts Institute of Technology
Predictive Allostatic Organization in Recurrent and Spiking Agents Under Partial Observability
Aug 11, 2026Frederick HayesPartially Observable RL Recurrent Neural Networks
Independent Researcher San Antonio, Texas, USA
Recurrent Neural Networks Beyond Time: Learning from Multiple Ordered Projections
Aug 10, 2026Vagan Terziyan, Artur Terziian, Oleksandra VitkoMulti-View Learning Recurrent Neural Networks
Faculty of Information Technology, University of Jyväskylä, FINLAND · Faculty of Informatics and Statistics, Prague University of Economics and Business, Czech Republic · Department of Artificial Intelligence, Kharkiv National University of Radio Electronics, Ukraine
Effective pruning of task-trained recurrent neural networks using noisy fluctuations and connection rescaling
Aug 5, 2026Sanjith Senthil, Rishidev ChaudhuriRecurrent Neural Networks Biologically Plausible Learning
1The Harker School, San Jose, CA 95129, USA · Department of Neurobiology, Physiology and Behavior, University of California, Davis, Davis CA 95616 · Department of Mathematics, University of California, Davis, Davis CA 95616 +1
Benchmarking Deep Learning Models for Dense Event Classification of Offshore Wind Infrastructure in Sentinel-1 Time Series
Aug 5, 2026Thorsten Hoeser, Felix Bachofer, Claudia KuenzerTime Series Classification Recurrent Neural Networks
Earth Observation Center (EOC), German Aerospace Center (DLR), Oberpfaffenhofen, 82234 Wessling, Germany · Institute for Geography and Geology, University of Wuerzburg, 97074 Wuerzburg, Germany
State Propagation Also Satisfies: A Complex-Valued State-Space Model for Deterministic State Tracking
Aug 4, 2026Xiaohe Li, Yang LuRecurrent Neural Networks State Tracking
GuangDong Police College · Department of Computer Science and Technology, School of Informatics, Xiamen University
Divisive Normalization Shapes Low-Rank Slow Manifolds for Continuous Working Memory
Aug 3, 2026Zhaotian Gu, Jie Su, Weiwei Wang +3Recurrent Neural Networks Continuous Attractor Neural Networks
School of System Science, Beijing Normal University · Qiyuan Laboratory · State Key Laboratory of Cognitive Neuroscience and Learning, Beijing Normal University
Interpretable Machine Learning for Traffic Congestion Prediction: Unveiling the Impact of Different COVID-19 Periods
Aug 2, 2026Dan Zhu, Chi Sin Ng, Litian Xie +1Time Series Forecasting Recurrent Neural Networks
Department of Civil and Environmental Engineering, National University of Singapore, Singapore · Department of Industrial Systems Engineering and Management, National University of Singapore, Singapore
Phoneme- vs. Character-Level Targets and Selective State-Space Models for Intracortical Brain-to-Text
Jul 29, 2026Lucas Zamora Vera, Jose A. Gonzalez-LopezSelective SSMs Neural Decoding
Universitat Oberta de Catalunya (UOC), Spain · Dpt. of Signal Theory, Telematics and Communications, University of Granada, Spain · Research Centre for Information and Communication Technologies (CITIC-UGR), University of Granada, Spain
The Sparsity Ceiling: Where Spiking Networks Can and Cannot Trade Activity for Energy
Jul 29, 2026Zeyu WangEfficient Neural Network Inference Spiking Transformers
Georgia Institute of Technology
Sensitivity Analysis of GRU, LSTM and Transformer Encoder in Classification of Automated Driving Systems
Jul 25, 2026Bidhya Shrestha, Christos PapadopoulosTransformer Time Series Classification
University of Memphis
Memoir: Should a Model Write to Its Memory While It Thinks?
Jul 22, 2026Jaber Jaber, Osama JaberMemory-Augmented Neural Networks Recurrent Neural Networks
RightNow AI
Cumsum-Composable Phase Transport for Low-Cost Streaming Keyword Spotting
Jul 22, 2026Mahesh GodavartiKeyword Spotting Recurrent Neural Networks
A Carrot, Inc
Time Series Network Utilization KPI Forecasting Using Advanced AI/ML Models
Jul 22, 2026Niraj Gadhe, Kirti Bhardwaj, Moulik Jain +2Time Series Forecasting Forecasting Benchmarks
Independent Researcher
Real-time optimal control with shallow recurrent decoder networks
Jul 21, 2026Matteo Tomasetto, Francesco Braghin, J. Nathan Kutz +1Recurrent Neural Networks Reduced-Order Modeling
Department of Mechanical Engineering, Politecnico di Milano, Milano, Italy · Autodesk Research, London, UK · MOX - Department of Mathematics, Politecnico di Milano, Milano, Italy
A Comparative Analysis of Machine Learning Models for Long and Short-Term Forecasting of the Egyptian Stock Market: A Focus on EGX30
Jul 15, 2026Muhammed Walid, Ahmed El-Naeimy, Hosam Moubarak +1Gated Recurrent Unit Long-Term Time Series Forecasting
Cyber Physical Lab, Department of Computer Science & Engineering · Egypt-Japan University Of Science and Technology, Alexandria, Egypt · Accounting Department +1
FAD-SA-GRU: Enhancing Hate Speech Detection in Algerian Dialect Through Feature-Augmented Self-Attention GRU Networks
Jul 13, 2026Sara Yakoubi, Ikram Khalfallah, Kenza Khelkhal +1Recurrent Neural Networks Hate Speech Detection
USTHB · ATM Mobilis
Emergent Generalization by Representation Learning in Artificial Neural Networks
Jul 11, 2026Hardik Rajpal, Dan GoodmanNeural Network Generalization Representation Learning
1I-X Centre for AI in Science, Imperial College London, W12 0BZ, UK · Department of Electrical and Electronic Engineering, Imperial College London, SW7 2AZ, UK
Exploratory Analysis of Deep Learning Models for Forecasting Meteorological Parameters in the Agricultural Sector
Jul 11, 2026Piotr Sikora, Sotirios KontogiannisConvolutional RNNs Multivariate Time Series Forecasting
Faculty of Technical Physics, Information Technology and Applied Mathematics Lodz Universtiy of Technlogy · MicroComputer Systems Laboratory Dept. of Mathematics University of Ioannina
Robustly Invertible Nonlinear Dynamics and the BiLipREN: From Inversion-Based Control to Generative Trajectory Modelling
Jul 10, 2026Yurui Zhang, Ruigang Wang, Ian R. ManchesterInvertible Neural Networks Recurrent Neural Networks
Australian Centre for Robotics (ACFR), and the School of Aerospace, Mechanical and Mechatronic Engineering, The University of Sydney, Australia
Letter Lemmatization: One-to-one and Banded RNNs for Reversing Character-Set Simplification and Abbreviation in Medieval Text
Jul 10, 2026Anguelos Nicolaou, Maria Pia Tiseo, Tamas Kovacs +2Recurrent Neural Networks Optical Character Recognition
University of Graz, Graz, Austria · University of Basel, Basel, Switzerland · Universit`a degli Studi di Napoli Federico II, Naples, Italy
LEXIC: Lightweight On-Device Decoding of Reading Comprehension from Eye Movements
Jul 9, 2026Sumin Lee, Kyeonghun Kim, Subeen Lee +5Recurrent Neural Networks Eye Tracking
Seoul National University · OUTTA · NVIDIA
Evaluating the Effect of Frame Rate in Sequence-Based Classification of Autism-Related Self-Stimulatory Hand Idiosyncrasies
Jul 8, 2026Raunak Mondal, Peter WashingtonData Augmentation Human Activity Recognition
School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA · Department of Information and Computer Sciences, University of Hawaiʻi at Mānoa, Honolulu, HI, USA
Unveiling Public Opinion: A Study of Sentiment Analysis Using LSTM and Traditional Models
Jul 8, 2026Atiq Ur RehmanSocial Media Analysis Sentiment Analysis
Department of Economics and Decision Sciences, University of South Dakota, USA

Aug 26, 2026J/K move · Enter open · S save

Scalable Multi-GPU Simulation of 3D Multicellular Growth with RNN-Based Workload Balancing

Matvey Moisseyev, Huijing Du, Dandan Zheng, Chi Zhang+1

School of Computing, University of Nebraska–Lincoln · Department of Mathematics, University of Nebraska–Lincoln · Department of Radiation Oncology, University of Rochester Medical Center+2

Domain Decomposition Methods Recurrent Neural Networks

Open paper AskPDF arXiv

Detailed multicellular growth simulations based on subcellular element models (SEMs) can capture complex tissue development, but their element-level interactions impose substantial computational cost. This work presents a scalable multi-GPU framework for 3D multicellular growth simulation that combines GPU acceleration, spatial binning, domain decomposition, and workload-aware partitioning. Cell movement, growth, and division continuously reshape the spatial workload distribution, causing initially balanced partitions to become inefficient over time. To address this, we introduce an RNN-based load-balancing controller that observes recent per-rank execution times and partition states and learns residual corrections to a reactive boundary-adjustment rule. The controller is trained offline in a differentiable surrogate of the load-balancing loop with randomized workload dynamics, requiring no measured execution traces for training. We evaluate the framework in terms of single-GPU acceleration, multi-GPU computation scaling, controller-level load-balancing behavior, and end-to-end simulation performance, with comparisons against static partitioning, reactive load balancing, and conventional time-series prediction baselines. A representative embryonic epidermal development use case further demonstrates the type of spatially and temporally evolving workload targeted by the framework. In our evaluation, GPU acceleration with spatial binning accelerates the interaction computation by roughly three orders of magnitude over a serial CPU baseline. RNN-guided load balancing reduces the mean global imbalance from 11.3% under static partitioning to 3.5%, lowers end-to-end runtime by 9.0% relative to static partitioning, and reduces slice migration by 7.7x compared with the reactive baseline, showing that history-aware control can improve workload balance while avoiding unnecessary repartitioning.