🧬Architectures

Recurrent Networks

RNNs, LSTMs, and sequential models

100 papers461 total citations
Compare with other topics
Feb '24 — Jan '26185 papers
Also includes: recurrent neural networks, rnn, lstm, gru, sequence modeling

Top Papers

#1

RNNs are not Transformers (Yet): The Key Bottleneck on In-Context Retrieval

Kaiyue Wen, Xingyu Dang, Kaifeng Lyu

ICLR 2025
48
citations
#2

TC-LIF: A Two-Compartment Spiking Neuron Model for Long-Term Sequential Modelling

Shimin Zhang, Qu Yang, Chenxiang Ma et al.

AAAI 2024arXiv:2308.13250
spiking neural networkstemporal classification tasksneuromorphic computing systemslong-term temporal dependency+4
41
citations
#3

Parallelizing non-linear sequential models over the sequence length

Yi Heng Lim, Qi Zhu, Joshua Selfridge et al.

ICLR 2024
28
citations
#4

TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning

Andreas Auer, Patrick Podest, Daniel Klotz et al.

NeurIPS 2025
26
citations
#5

EAS-SNN: End-to-End Adaptive Sampling and Representation for Event-based Detection with Recurrent Spiking Neural Networks

Ziming Wang, Ziling Wang, Huaning Li et al.

ECCV 2024arXiv:2403.12574
event camerasadaptive event samplingspiking neural networksobject detection+3
24
citations
#6

DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products

Julien Siems, Timur Carstensen, Arber Zela et al.

NeurIPS 2025
23
citations
#7

Exploring the Promise and Limits of Real-Time Recurrent Learning

Kazuki Irie, Anand Gopalakrishnan, Jürgen Schmidhuber

ICLR 2024
20
citations
#8

LMUFormer: Low Complexity Yet Powerful Spiking Model With Legendre Memory Units

Zeyu Liu, Gourav Datta, Anni Li et al.

ICLR 2024
17
citations
#9

xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories

Maurice Kraus, Felix Divo, Devendra Singh Dhami et al.

NeurIPS 2025
16
citations
#10

Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks

Mingqing Xiao, Qingyan Meng, Zongpeng Zhang et al.

ICLR 2024
13
citations
#11

Long-Sequence Recommendation Models Need Decoupled Embeddings

Ningya Feng, Junwei Pan, Jialong Wu et al.

ICLR 2025arXiv:2410.02604
long-sequence recommendationattention mechanismuser behavior modelingembedding decoupling+2
11
citations
#12

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks

Thomas Schmied, Thomas Adler, Vihang Patil et al.

ICML 2025
10
citations
#13

Scalable Real-Time Recurrent Learning Using Columnar-Constructive Networks

Khurram Javed, Haseeb Shah, Richard Sutton et al.

ICLR 2024
10
citations
#14

Plastic Learning with Deep Fourier Features

Alex Lewandowski, Dale Schuurmans, Marlos C. Machado

ICLR 2025
9
citations
#15

Random-Set Neural Networks

Shireen Kudukkil Manchingal, Muhammad Mubashar, Kaizheng Wang et al.

ICLR 2025
9
citations
#16

IVP-VAE: Modeling EHR Time Series with Initial Value Problem Solvers

Jingge Xiao, Leonie Basso, Wolfgang Nejdl et al.

AAAI 2024arXiv:2305.06741
irregularly sampled time serieselectronic health recordsinitial value problem solverscontinuous-time models+3
8
citations
#17

Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks

Lukas Braun, Erin Grant, Andrew Saxe

ICML 2025
8
citations
#18

Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels

Maximilian Beck, Korbinian Pöppel, Phillip Lippe et al.

NeurIPS 2025arXiv:2503.14376
attention mechanismlinear rnnskernel optimizationlong-context modeling+3
8
citations
#19

LORS: Low-rank Residual Structure for Parameter-Efficient Network Stacking

Jialin Li, Qiang Nie, Weifu Fu et al.

CVPR 2024
7
citations
#20

The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks.

Aaron Spieler, Nasim Rahaman, Georg Martius et al.

ICLR 2024
7
citations
#21

In-context Time Series Predictor

Jiecheng Lu, Yan Sun, Shihao Yang

ICLR 2025
7
citations
#22

BRAID: Input-driven Nonlinear Dynamical Modeling of Neural-Behavioral Data

Parsa Vahidi, Omid G. Sani, Maryam Shanechi

ICLR 2025
7
citations
#23

Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Models

Benjamin Walker, Lingyi Yang, Nicola Muca Cirone et al.

NeurIPS 2025arXiv:2505.17761
controlled differential equationsstate-transition matricessequence modelingparallel-in-time computation+3
6
citations
#24

Expand and Compress: Exploring Tuning Principles for Continual Spatio-Temporal Graph Forecasting

Wei Chen, Yuxuan Liang

ICLR 2025
6
citations
#25

Building Variable-Sized Models via Learngene Pool

Boyu Shi, Shiyu Xia, Xu Yang et al.

AAAI 2024arXiv:2312.05743
stitchable neural networkslearngene frameworkknowledge distillationvariable-sized models+4
5
citations
#26

NetFormer: An interpretable model for recovering dynamical connectivity in neuronal population dynamics

Ziyu Lu, Wuwei Zhang, Trung Le et al.

ICLR 2025
5
citations
#27

Spike-Temporal Latent Representation for Energy-Efficient Event-to-Video Reconstruction

Jianxiong Tang, Jian-Huang Lai, Lingxiao Yang et al.

ECCV 2024
5
citations
#28

Real-Time Recurrent Reinforcement Learning

Julian Lemmel, Radu Grosu

AAAI 2025
5
citations
#29

Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness

Kangrui Du, Yuhang Wu, Shikuang Deng et al.

ICLR 2025arXiv:2503.17394
spiking neural networkstemporal flexibilitymixed time-step trainingneuromorphic hardware+3
5
citations
#30

Transformative or Conservative? Conservation laws for ResNets and Transformers

Sibylle Marcotte, Rémi Gribonval, Gabriel Peyré

ICML 2025
4
citations
#31

Scaling Up Liquid-Resistance Liquid-Capacitance Networks for Efficient Sequence Modeling

Mónika Farsang, Radu Grosu

NeurIPS 2025
4
citations
#32

Efficient Logit-based Knowledge Distillation of Deep Spiking Neural Networks for Full-Range Timestep Deployment

Chengting Yu, Xiaochen Zhao, Lei Liu et al.

ICML 2025
4
citations
#33

Exploiting Symmetric Temporally Sparse BPTT for Efficient RNN Training

Xi Chen, Chang Gao, Zuowen Wang et al.

AAAI 2024arXiv:2312.09391
recurrent neural networkstemporal sparsitybackpropagation through timeedge computing training+4
4
citations
#34

Proxy Target: Bridging the Gap Between Discrete Spiking Neural Networks and Continuous Control

Zijie Xu, Tong Bu, Zecheng Hao et al.

NeurIPS 2025arXiv:2505.24161
spiking neural networkscontinuous controlreinforcement learningneuromorphic hardware+4
3
citations
#35

Make Haste Slowly: A Theory of Emergent Structured Mixed Selectivity in Feature Learning ReLU Networks

Devon Jarvis, Richard Klein, Benjamin Rosman et al.

ICLR 2025
3
citations
#36

Learning long range dependencies through time reversal symmetry breaking

Guillaume Pourcel, Maxence Ernoult

NeurIPS 2025
3
citations
#37

Parallel Sequence Modeling via Generalized Spatial Propagation Network

Hongjun Wang, Wonmin Byeon, Jiarui Xu et al.

CVPR 2025arXiv:2501.12381
attention mechanismspatial propagation networkvision tasks2d spatial structures+4
3
citations
#38

Learning In-context $n$-grams with Transformers: Sub-$n$-grams Are Near-Stationary Points

Aditya Vardhan Varre, Gizem Yüce, Nicolas Flammarion

ICML 2025
3
citations
#39

STRAP: Spatio-Temporal Pattern Retrieval for Out-of-Distribution Generalization

Haoyu Zhang, WentaoZhang, Hao Miao et al.

NeurIPS 2025arXiv:2505.19547
spatio-temporal graph neural networksout-of-distribution generalizationretrieval-augmented learningdynamic graph-structured data+3
3
citations
#40

PAC-Bayes Generalisation Bounds for Dynamical Systems including Stable RNNs

Deividas Eringis, John Leth, Zheng-Hua Tan et al.

AAAI 2024arXiv:2312.09793
pac-bayes boundsgeneralization gapdynamical systemsstable recurrent neural networks+4
3
citations
#41

BARNN: A Bayesian Autoregressive and Recurrent Neural Network

Dario Coscia, Max Welling, Nicola Demo et al.

ICML 2025
3
citations
#42

Sequence Complementor: Complementing Transformers for Time Series Forecasting with Learnable Sequences

Xiwen Chen, Peijie Qiu, Wenhui Zhu et al.

AAAI 2025
2
citations
#43

GRSN: Gated Recurrent Spiking Neurons for POMDPs and MARL

Lang Qin, Ziming Wang, Runhao Jiang et al.

AAAI 2025
2
citations
#44

Learning Spatiotemporal Dynamical Systems from Point Process Observations

Valerii Iakovlev, Harri Lähdesmäki

ICLR 2025arXiv:2406.00368
spatiotemporal dynamicspoint process observationsneural differential equationsneural point processes+3
2
citations
#45

Dendritic Resonate-and-Fire Neuron for Effective and Efficient Long Sequence Modeling

Dehao Zhang, Malu Zhang, Shuai Wang et al.

NeurIPS 2025arXiv:2509.17186
resonate-and-fire neuronslong sequence modelingdendritic neuron modelsspatiotemporal spike trains+4
2
citations
#46

Transformers for Mixed-type Event Sequences

Felix Draxler, Yang Meng, Kai Nelson et al.

NeurIPS 2025
2
citations
#47

LOCORE: Image Re-ranking with Long-Context Sequence Modeling

Zilin Xiao, Pavel Suma, Ayush Sachdeva et al.

CVPR 2025
2
citations
#48

TS-SNN: Temporal Shift Module for Spiking Neural Networks

Kairong Yu, Tianqing Zhang, Qi Xu et al.

ICML 2025
2
citations
#49

Multiplication-Free Parallelizable Spiking Neurons with Efficient Spatio-Temporal Dynamics

Peng Xue, Wei Fang, Zhengyu Ma et al.

NeurIPS 2025
1
citations
#50

Position: Solve Layerwise Linear Models First to Understand Neural Dynamical Phenomena (Neural Collapse, Emergence, Lazy/Rich Regime, and Grokking)

Yoonsoo Nam, Seok Hyeong Lee, Clémentine Dominé et al.

ICML 2025
1
citations
#51

Learning the Plasticity: Plasticity-Driven Learning Framework in Spiking Neural Networks

Guobin Shen, Dongcheng Zhao, Yiting Dong et al.

NeurIPS 2025arXiv:2308.12063
spiking neural networkssynaptic plasticityplasticity-driven learningworking memory enhancement+3
1
citations
#52

Accelerated training through iterative gradient propagation along the residual path

Erwan Fagnou, Paul Caillon, Blaise Delattre et al.

ICLR 2025
1
citations
#53

Revisiting Bi-Linear State Transitions in Recurrent Neural Networks

Reza Ebrahimi, Roland Memisevic

NeurIPS 2025
1
citations
#54

HADAMRNN: BINARY AND SPARSE TERNARY ORTHOGONAL RNNS

Armand Foucault, Francois Malgouyres, Franck Mamalet

ICLR 2025
1
citations
#55

Martingale Posterior Neural Networks for Fast Sequential Decision Making

Gerardo Duran-Martin, Leandro Sánchez-Betancourt, Alvaro Cartea et al.

NeurIPS 2025
1
citations
#56

Information Bottleneck-guided MLPs for Robust Spatial-temporal Forecasting

Min Chen, Guansong Pang, Wenjun Wang et al.

ICML 2025
1
citations
#57

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs

Qijun Luo, Mengqi Li, Lei Zhao et al.

NeurIPS 2025
1
citations
#58

Improving Bilinear RNN with Closed-loop Control

Jiaxi Hu, Yongqi Pan, Jusen Du et al.

NeurIPS 2025
1
citations
#59

Locally Connected Echo State Networks for Time Series Forecasting

Filip Matzner, František Mráz

ICLR 2025
echo state networksreservoir computingtime series forecastinglocally connected reservoirs+4
1
citations
#60

RHYTHM: Reasoning with Hierarchical Temporal Tokenization for Human Mobility

Haoyu He, Haozheng Luo, Yan Chen et al.

NeurIPS 2025
1
citations
#61

Learning Successor Features with Distributed Hebbian Temporal Memory

Evgenii Dzhivelikian, Petr Kuderov, Aleksandr Panov

ICLR 2025
1
citations
#62

Learning Chaos In A Linear Way

Xiaoyuan Cheng, Yi He, Yiming Yang et al.

ICLR 2025
—
not collected
#63

Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues

Riccardo Grazzi, Julien Siems, Arber Zela et al.

ICLR 2025
—
not collected
#64

Repetition Improves Language Model Embeddings

Jacob Springer, Suhas Kotha, Daniel Fried et al.

ICLR 2025
—
not collected
#65

Self-Normalized Resets for Plasticity in Continual Learning

Vivek Farias, Adam Jozefiak

ICLR 2025
—
not collected
#66

TGB-Seq Benchmark: Challenging Temporal GNNs with Complex Sequential Dynamics

Lu Yi, Jie Peng, Yanping Zheng et al.

ICLR 2025
—
not collected
#67

Deep Non-Rigid Structure-from-Motion Revisited: Canonicalization and Sequence Modeling

Hui Deng, Jiawei Shi, Zhen Qin et al.

AAAI 2025
—
not collected
#68

Iterative Sparse Attention for Long-sequence Recommendation

Guanyu Lin, Jinwei Luo, Yinfeng Li et al.

AAAI 2025
—
not collected
#69

LS-TGNN: Long and Short-Term Temporal Graph Neural Network for Session-Based Recommendation

Zhonghong Ou, Xiao Zhang, Yifan Zhu et al.

AAAI 2025
—
not collected
#70

Scalable Trajectory-User Linking with Dual-Stream Representation Networks

Hao Zhang, Wei Chen, Xingyu Zhao et al.

AAAI 2025
—
not collected
#71

FSTA-SNN:Frequency-Based Spatial-Temporal Attention Module for Spiking Neural Networks

Kairong Yu, Tianqing Zhang, Hongwei Wang et al.

AAAI 2025
—
not collected
#72

TNPAR: Topological Neural Poisson Auto-Regressive Model for Learning Granger Causal Structure from Event Sequences

Authors: Yuequn Liu, Ruichu Cai, Wei Chen et al.

AAAI 2024
—
not collected
#73

Temporal Graph Contrastive Learning for Sequential Recommendation

Shengzhe Zhang, Liyi Chen, Chao Wang et al.

AAAI 2024
—
not collected
#74

Complexity of Neural Network Training and ETR: Extensions with Effectively Continuous Functions

Teemu Hankala, Miika Hannula, Juha Kontinen et al.

AAAI 2024
—
not collected
#75

On the Expressivity of Recurrent Neural Cascades

Nadezda Knorozova, Alessandro Ronca

AAAI 2024arXiv:2312.09048
recurrent neural cascadesstar-free regular languagesconstructive learning methodsacyclic recurrent networks+4
—
not collected
#76

6385 Efficient Spiking Neural Networks with Sparse Selective Activation for Continual Learning

Jiangrong Shen, Wenyao Ni, Qi Xu et al.

AAAI 2024
—
not collected
#77

Instance-Conditional Timescales of Decay for Nonstationary Learning

Nishant Jain, Pradeep Shenoy

AAAI 2024
—
not collected
#78

Discovering Sequential Patterns with Predictable Inter-event Delays

Joscha Cüppers, Paul Krieger, Jilles Vreeken

AAAI 2024
—
not collected
#79

Memory-Efficient Reversible Spiking Neural Networks

Hong Zhang, Yu Zhang

AAAI 2024
—
not collected
#80

Dr2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning

Chen Zhao, Shuming Liu, Karttikeya Mangalam et al.

CVPR 2024
—
not collected
#81

Incremental Residual Concept Bottleneck Models

Chenming Shang, Shiji Zhou, Hengyuan Zhang et al.

CVPR 2024
—
not collected
#82

Online Stabilization of Spiking Neural Networks

Yaoyu Zhu, Jianhao Ding, Tiejun Huang et al.

ICLR 2024
—
not collected
#83

Critical Learning Periods Emerge Even in Deep Linear Networks

Michael Kleinman, Alessandro Achille, Stefano Soatto

ICLR 2024
—
not collected
#84

SineNet: Learning Temporal Dynamics in Time-Dependent Partial Differential Equations

Xuan Zhang, Jacob Helwig, Yuchao Lin et al.

ICLR 2024
—
not collected
#85

Leveraging Low-Rank and Sparse Recurrent Connectivity for Robust Closed-Loop Control

Neehal Tumma, Mathias Lechner, Noel Loo et al.

ICLR 2024
—
not collected
#86

Parsing neural dynamics with infinite recurrent switching linear dynamical systems

Victor Geadah, International Brain Laboratory, Jonathan Pillow

ICLR 2024
—
not collected
#87

On the Markov Property of Neural Algorithmic Reasoning: Analyses and Methods

Montgomery Bohde, Meng Liu, Alexandra Saxton et al.

ICLR 2024
—
not collected
#88

Learning From Simplicial Data Based on Random Walks and 1D Convolutions

Florian Frantzen, Michael Schaub

ICLR 2024
—
not collected
#89

Inverse Approximation Theory for Nonlinear Recurrent Neural Networks

Shida Wang, Zhong Li, Qianxiao Li

ICLR 2024
—
not collected
#90

Successor Heads: Recurring, Interpretable Attention Heads In The Wild

Rhys Gould, Euan Ong, George Ogden et al.

ICLR 2024
—
not collected
#91

Implicit regularization of deep residual networks towards neural ODEs

Pierre Marion, Yu-Han Wu, Michael Sander et al.

ICLR 2024
—
not collected
#92

A Progressive Training Framework for Spiking Neural Networks with Learnable Multi-hierarchical Model

Zecheng Hao, Xinyu Shi, Zihan Huang et al.

ICLR 2024
—
not collected
#93

Function-space Parameterization of Neural Networks for Sequential Learning

Aidan Scannell, Riccardo Mereu, Paul Chang et al.

ICLR 2024
—
not collected
#94

Scalable Monotonic Neural Networks

Hyunho Kim, Jong-Seok Lee

ICLR 2024
—
not collected
#95

A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networks

Tommaso Salvatori, Yuhang Song, Yordan Yordanov et al.

ICLR 2024
—
not collected
#96

Complex priors and flexible inference in recurrent circuits with dendritic nonlinearities

Benjamin Lyo, Cristina Savin

ICLR 2024
—
not collected
#97

Sufficient conditions for offline reactivation in recurrent neural networks

Nanda H Krishna, Colin Bredenberg, Daniel Levenstein et al.

ICLR 2024
—
not collected
#98

Sparse Spiking Neural Network: Exploiting Heterogeneity in Timescales for Pruning Recurrent SNN

Biswadeep Chakraborty, Beomseok Kang, Harshit Kumar et al.

ICLR 2024
—
not collected
#99

ModernTCN: A Modern Pure Convolution Structure for General Time Series Analysis

DongHao Luo, Xue Wang

ICLR 2024
—
not collected
#100

Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings

Ilyass Hammouamri, Ismail Khalfaoui Hassani, Timothée Masquelier

ICLR 2024
—
not collected