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 86 篇，第 2 / 2 页

51. ICML 2025Lego Sketch: A Scalable Memory-augmented Neural Network for Sketching Data Streams
52. ICML 2025Liger: Linearizing Large Language Models to Gated Recurrent Structures
53. ICML 2025Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models
54. ICML 2025Minerva: A Programmable Memory Test Benchmark for Language Models
55. ICML 2025Oracle-MoE: Locality-preserving Routing in the Oracle Space for Memory-constrained Large Language Model Inference
56. ICML 2025Pixel2Feature Attack (P2FA): Rethinking the Perturbed Space to Enhance Adversarial Transferability
57. ICML 2025Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models
58. ICML 2025Quantifying Memory Utilization with Effective State-Size
59. ICML 2025Tensor Decomposition Based Memory-Efficient Incremental Learning
60. ICML 2024Achieving Lossless Gradient Sparsification via Mapping to Alternative Space in Federated Learning
61. ICML 2024Dynamic Metric Embedding into lp Space
62. ICML 2024Hidden Traveling Waves bind Working Memory Variables in Recurrent Neural Networks
63. ICML 2024Hieros: Hierarchical Imagination on Structured State Space Sequence World Models
64. ICML 2024How to Explore with Belief: State Entropy Maximization in POMDPs
65. ICML 2024Learning Latent Space Hierarchical EBM Diffusion Models
66. ICML 2024Learning the Target Network in Function Space
67. ICML 2024Learning Useful Representations of Recurrent Neural Network Weight Matrices
68. ICML 2024Memory Efficient Neural Processes via Constant Memory Attention Block
69. ICML 2024Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning
70. ICML 2024PAC-Bayesian Error Bound, via Rényi Divergence, for a Class of Linear Time-Invariant State-Space Models
71. ICML 2024Recurrent Distance Filtering for Graph Representation Learning
72. ICML 2024Recurrent Early Exits for Federated Learning with Heterogeneous Clients
73. ICML 2024Repeat After Me: Transformers are Better than State Space Models at Copying
74. ICML 2024Simple linear attention language models balance the recall-throughput tradeoff
75. ICML 2024Sobolev Space Regularised Pre Density Models
76. ICML 2024StableSSM: Alleviating the Curse of Memory in State-space Models through Stable Reparameterization
77. ICML 2024State-Free Inference of State-Space Models: The *Transfer Function* Approach
78. ICML 2024The Illusion of State in State-Space Models
79. ICML 2024Think Before You Act: Decision Transformers with Working Memory
80. ICML 2023A Picture of the Space of Typical Learnable Tasks
81. ICML 2023DIVISION: Memory Efficient Training via Dual Activation Precision
82. ICML 2023General Sequential Episodic Memory Model
83. ICML 2023Memory-Based Meta-Learning on Non-Stationary Distributions
84. ICML 2023Orthogonality-Enforced Latent Space in Autoencoders: An Approach to Learning Disentangled Representations
85. ICML 2023Resurrecting Recurrent Neural Networks for Long Sequences
86. ICML 2023Sequence Modeling with Multiresolution Convolutional Memory

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。