Recurrent Memory papers, 2023–2026

Key findings

• Recurrent Memory went from 45 papers in 2023 to 172 in 2026, roughly 3.8x in three years.
• NeurIPS publishes the most Recurrent Memory work: 186 papers from 2023 to 2026, 45% of the four-venue total.
• The fastest-growing overlap is with Multimodal LLMs: papers tagged with both rose from 0 in 2023 to 15 in 2026.
• Among the 5 topics under Long Context and Memory, it ranks #2 by 2026 paper count; the fastest grower in the group, Retrieval Memory, is up 6.6x versus 3.8x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026Approximate Memory Suffices for Universal Approximation with State Space Models
• ICML 2026An Algebraic View of the Expressivity of Recurrent Language Models
• ICLR 2026Exploring State-Space Models for Data-Specific Neural Representations
• CVPR 2026Coupling Liquid Time-Constant Encoders with Modern Hopfield Memory
• NeurIPS 2025Bridging Expressivity and Scalability with Adaptive Unitary SSMs
• ICML 2025Oracle-MoE: Locality-preserving Routing in the Oracle Space for Memory-constrained Large Language Model Inference
• ICLR 2025Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space Models
• CVPR 2025Breaking the Memory Barrier of Contrastive Loss via Tile-Based Strategy
• NeurIPS 2024Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective
• ICML 2024Hidden Traveling Waves bind Working Memory Variables in Recurrent Neural Networks
• ICLR 2024A 2-Dimensional State Space Layer for Spatial Inductive Bias
• CVPR 2024GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objects
• NeurIPS 2023Hypothesis Selection with Memory Constraints
• ICML 2023A Picture of the Space of Typical Learnable Tasks
• ICLR 2023Associative Memory Augmented Asynchronous Spatiotemporal Representation Learning for Event-based Perception
• CVPR 2023Bilateral Memory Consolidation for Continual Learning
• NeurIPS 2026Commutator Memory: Sparse, Path-Local Reading and Steering in Language Models
• ICML 2026Do Transformers Need Three Projections? Systematic Study of QKV Variants
• ICLR 2026On the Expressiveness of State Space Models via Temporal Logics
• CVPR 2026DREAM Document Recognition with Explicit Adaptive Memory

All Recurrent Memory papers

416 papers, page 5 of 9

201. ICLR 2025Lipschitz Bandits in Optimal Space
202. ICLR 2025Locally Connected Echo State Networks for Time Series Forecasting
203. ICLR 2025MIRACLE 3D: Memory-efficient Integrated Robust Approach for Continual Learning on 3D Point Clouds via Shape Model Construction
204. ICLR 2025On the Benefits of Memory for Modeling Time-Dependent PDEs
205. ICLR 2025Oscillatory State-Space Models
206. ICLR 2025Quamba: A Post-Training Quantization Recipe for Selective State Space Models
207. ICLR 2025Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
208. ICLR 2025State Space Models are Provably Comparable to Transformers in Dynamic Token Selection
209. ICLR 2025Towards Continuous Reuse of Graph Models via Holistic Memory Diversification
210. ICLR 2025Tuning Frequency Bias of State Space Models
211. ICLR 2025Ultra-Sparse Memory Network
212. ICLR 2025Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues
213. ICML 2025Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity
214. ICML 2025Dynamical phases of short-term memory mechanisms in RNNs
215. ICML 2025Flow-field inference from neural data using deep recurrent networks
216. ICML 2025From Weight-Based to State-Based Fine-Tuning: Further Memory Reduction on LoRA with Parallel Control
217. ICML 2025FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training
218. ICML 2025Identifying Neural Dynamics Using Interventional State Space Models
219. ICML 2025Learning dynamics in linear recurrent neural networks
220. ICML 2025Lego Sketch: A Scalable Memory-augmented Neural Network for Sketching Data Streams
221. ICML 2025Liger: Linearizing Large Language Models to Gated Recurrent Structures
222. ICML 2025Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models
223. ICML 2025Minerva: A Programmable Memory Test Benchmark for Language Models
224. ICML 2025Oracle-MoE: Locality-preserving Routing in the Oracle Space for Memory-constrained Large Language Model Inference
225. ICML 2025Pixel2Feature Attack (P2FA): Rethinking the Perturbed Space to Enhance Adversarial Transferability
226. ICML 2025Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models
227. ICML 2025Quantifying Memory Utilization with Effective State-Size
228. ICML 2025Tensor Decomposition Based Memory-Efficient Incremental Learning
229. NeurIPS 2025Bridging Expressivity and Scalability with Adaptive Unitary SSMs
230. NeurIPS 2025Computation and Memory-Efficient Model Compression with Gradient Reweighting
231. NeurIPS 2025Cost-Efficient LLM Training with Lifetime-Aware Tensor Offloading via GPUDirect Storage
232. NeurIPS 2025Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation
233. NeurIPS 2025DeltaFormer: Unlock the state space of Transformer
234. NeurIPS 2025DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products
235. NeurIPS 2025DERD-Net: Learning Depth from Event-based Ray Densities
236. NeurIPS 2025DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs
237. NeurIPS 2025DyMoDreamer: World Modeling with Dynamic Modulation
238. NeurIPS 2025Efficient Allocation of Working Memory Resource for Utility Maximization in Humans and Recurrent Neural Networks
239. NeurIPS 2025Error Forcing in Recurrent Neural Networks
240. NeurIPS 2025Exponential Dynamic Energy Network for High Capacity Sequence Memory
241. NeurIPS 2025Fixed-Point RNNs: Interpolating from Diagonal to Dense
242. NeurIPS 2025FLAME: Fast Long-context Adaptive Memory for Event-based Vision
243. NeurIPS 2025Flow Equivariant Recurrent Neural Networks
244. NeurIPS 2025FRN: Fractal-Based Recursive Spectral Reconstruction Network
245. NeurIPS 2025Hankel Singular Value Regularization for Highly Compressible State Space Models
246. NeurIPS 2025Hardware-aligned Hierarchical Sparse Attention for Efficient Long-term Memory Access
247. NeurIPS 2025Inference of Whole Brain Electrophysiological Networks Through Multimodal Integration of Simultaneous Scalp and Intracranial EEG
248. NeurIPS 2025Inference-time Alignment in Continuous Space
249. NeurIPS 2025Irrational Complex Rotations Empower Low-bit Optimizers
250. NeurIPS 2025Kinaema: a recurrent sequence model for memory and pose in motion

FAQ

How many Recurrent Memory papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

416 in total: 45 in 2023, 82 in 2024, 117 in 2025, 172 in 2026.

How many Recurrent Memory papers are at NeurIPS 2026?

NeurIPS 2026 has 73 Recurrent Memory papers, versus 61 the year before.

How many Recurrent Memory papers are at ICLR 2026?

ICLR 2026 has 35 Recurrent Memory papers, versus 20 the year before.

How many Recurrent Memory papers are at ICML 2026?

ICML 2026 has 43 Recurrent Memory papers, versus 16 the year before.

How many Recurrent Memory papers are at CVPR 2026?

CVPR 2026 has 21 Recurrent Memory papers, versus 20 the year before.

Which conference publishes the most Recurrent Memory papers?

NeurIPS, with 186 papers from 2023 to 2026.