循环记忆论文趋势 2023–2026

主要结论

• 循环记忆论文从 2023 年的 45 篇增长到 2026 年的 172 篇，三年间扩大到约 3.8 倍。
• NeurIPS 是发循环记忆论文最多的会议，2023–2026 年共 186 篇，占四个会议总量的 45%。
• 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 15 篇。
• 在「长上下文与记忆」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的检索记忆是 6.6 倍，循环记忆是 3.8 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• 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

全部循环记忆论文

共 43 篇，第 1 / 1 页

1. ICML 2026Adaptive Memory Retention in Dynamic Graphs
2. ICML 2026An Algebraic View of the Expressivity of Recurrent Language Models
3. ICML 2026Biologically plausible heavy-tailed connectivity enhances generalizations on cognitive tasks in recurrent neural networks
4. ICML 2026DiffuMamba: High-Throughput Diffusion LMs with Mamba Backbone
5. ICML 2026Do Transformers Need Three Projections? Systematic Study of QKV Variants
6. ICML 2026Episodic Memory-Guided Controllable Experience Synthesis for Reinforcement Learning
7. ICML 2026FlashOptim: Optimizers for Memory-Efficient Training
8. ICML 2026Flow Equivariant World Models: Structured Memory for Dynamic Environments
9. ICML 2026FOAM: Blocked State Folding for Memory-Efficient LLM Training
10. ICML 2026FRACTAL: State Space Model with Fractional Recurrent Architecture for Computational Temporal Analysis of Long Sequences
11. ICML 2026Functional building blocks of neural networks: from network motifs to collective dynamics
12. ICML 2026Global Credit Assignment via Dynamical Criticality
13. ICML 2026HiPPO Zoo: Explicit Memory Mechanisms for Interpretable State Space Models
14. ICML 2026Hyperbolic Associative Memory Networks
15. ICML 2026Hyperbolic neural population geometry benefits computation
16. ICML 2026Information dynamics and Memory in Neural Networks through Fisher Information Diffusion
17. ICML 2026Interleaved Selective State Space Models for Efficient WiFi-Based 3D Multi-Person Pose Estimation
18. ICML 2026Investigating Memory in Model-Free RL with POPGym Arcade
19. ICML 2026Keeping a Secret Requires a Good Memory: Unconditional Streaming Lower-Bounds for Differentially Private Algorithms
20. ICML 2026Learning Long Range Spatio-Temporal Representations over Continuous Time Dynamic Graphs with State Space Models
21. ICML 2026LIF Recurrent Memory Enables Long-Horizon Spiking Computation
22. ICML 2026LightWM: Training-Free Hierarchical Working Memory for Small Language Model Agents
23. ICML 2026Memory as a Markov Matrix: Sample Efficient Knowledge Expansion via Token-to-Dictionary Mapping
24. ICML 2026Memory as Dynamics: Learning Reliability-Guided Predictive Models for Online Video Perception
25. ICML 2026Memory Caching: RNNs with Growing Memory
26. ICML 2026MIMOMamba: From Scalar Duality to Matrix-Valued Attention
27. ICML 2026MuonSSM: Orthogonalizing State Space Models for Sequence Modeling
28. ICML 2026On Structured State-Space Duality
29. ICML 2026On the "Induction Bias" in Sequence Models
30. ICML 2026On the Expressive Power of Permutation-Equivariant Weight-Space Networks
31. ICML 2026ParalESN: Enabling parallel information processing in Reservoir Computing
32. ICML 2026ProtoKV: Streaming Video Understanding under Delayed Query with Summary-State Memory
33. ICML 2026Q-Delta: Beyond Key–Value Associative State Evolution
34. ICML 2026Ramba: Selective State-Space Models for Relational Deep Learning
35. ICML 2026Rational Transductors
36. ICML 2026Recurrent Equivariant Constraint Modulation: Learning Per-Layer Symmetry Relaxation from Data
37. ICML 2026Recursive Binding on a Budget: Subspace Carving in Order-$p$ Tensor Memories
38. ICML 2026Retrieval-Aware Distillation for Transformer-SSM Hybrids
39. ICML 2026Score-Repellent Monte Carlo: Toward Efficient Non-Markovian Sampler with Constant Memory in General State Spaces
40. ICML 2026SF-Mamba: Rethinking State Space Model for Vision
41. ICML 2026SparseSSM: Efficient Selective Structured State Space Models Can Be Pruned in One-Shot
42. ICML 2026WaveSSM: Multiscale State-Space Models for Non-stationary Signal Attention
43. ICML 2026Why Linear Recurrent Memory Works in Partially Observable Reinforcement Learning

常见问题

2023–2026 年四大会议一共有多少篇循环记忆论文？

共 416 篇，按年份分别是 2023 年 45 篇、2024 年 82 篇、2025 年 117 篇、2026 年 172 篇。

NeurIPS 2026 有多少篇循环记忆论文？

NeurIPS 2026 有 73 篇循环记忆论文，上一届是 61 篇。

ICLR 2026 有多少篇循环记忆论文？

ICLR 2026 有 35 篇循环记忆论文，上一届是 20 篇。

ICML 2026 有多少篇循环记忆论文？

ICML 2026 有 43 篇循环记忆论文，上一届是 16 篇。

CVPR 2026 有多少篇循环记忆论文？

CVPR 2026 有 21 篇循环记忆论文，上一届是 20 篇。

哪个会议的循环记忆论文最多？

NeurIPS，2023–2026 年共 186 篇。