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 35 篇，第 1 / 1 页

1. ICLR 2026A Memory-Efficient Hierarchical Algorithm for Large-scale Optimal Transport Problems
2. ICLR 2026Adaptive Hopfield Network: Rethinking Similarities in Associative Memory
3. ICLR 2026AIRE-Prune: Asymptotic Impulse-Response Energy for State Pruning in State Space Models
4. ICLR 2026ChainGPT: Dual-Reasoning Model with Recurrent Depth and Multi-Rank State Updates
5. ICLR 2026Detecting Invariant Manifolds in ReLU-Based RNNs
6. ICLR 2026DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation
7. ICLR 2026Discovering alternative solutions beyond the simplicity bias in recurrent neural networks
8. ICLR 2026Dynamical properties of dense associative memory
9. ICLR 2026Exploring State-Space Models for Data-Specific Neural Representations
10. ICLR 2026Feedback-driven recurrent quantum neural network universality
11. ICLR 2026Forget Forgetting: Continual Learning in a World of Abundant Memory
12. ICLR 2026From movement to cognitive maps: recurrent neural networks reveal how locomotor development shapes hippocampal spatial coding
13. ICLR 2026Inferring brain plasticity rule under long-term stimulation with structured recurrent dynamics
14. ICLR 2026Latent Wasserstein Adversarial Imitation Learning
15. ICLR 2026Learning linear state-space models with sparse system matrices
16. ICLR 2026Mamba-3: Improved Sequence Modeling using State Space Principles
17. ICLR 2026MeSH: Memory-as-State-Highways for Recursive Transformers
18. ICLR 2026MoDr: Mixture-of-Depth-Recurrent Transformers for Test-Time Reasoning
19. ICLR 2026On the Expressiveness of State Space Models via Temporal Logics
20. ICLR 2026Quantized Gradient Projection for Memory-Efficient Continual Learning
21. ICLR 2026Recurrent Action Transformer with Memory
22. ICLR 2026Redirection for Erasing Memory (REM): Towards a universal unlearning method for corrupted data
23. ICLR 2026Sequential Parallel Duality in Prefix Scannable Models
24. ICLR 2026Setting up for failure: automatic discovery of the neural mechanisms of cognitive errors
25. ICLR 2026Smooth Reading: Bridging the Gap of Recurrent LLM to Self-Attention LLM on Long-Context Understanding
26. ICLR 2026SSDi8: Accurate and Efficient 8-bit Quantization for State Space Duality
27. ICLR 2026Sublinear Spectral Clustering Oracle with Little Memory
28. ICLR 2026Temporal superposition and feature geometry of RNNs under memory demands
29. ICLR 2026Test-Time Accuracy-Cost Control in Neural Simulators via Recurrent-Depth
30. ICLR 2026The Curious Case of In-Training Compression of State Space Models
31. ICLR 2026The Expressive Limits of Diagonal SSMs for State-Tracking
32. ICLR 2026The Pensieve Paradigm: Stateful Language Models with Learned Memory Management
33. ICLR 2026To Infinity and Beyond: Tool-Use Unlocks Length Generalization in State Space Models
34. ICLR 2026Tuning the burn-in phase in training recurrent neural networks improves their performance
35. ICLR 2026Weight-Space Linear Recurrent Neural Networks

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。