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 82 篇，第 2 / 2 页

51. ICLR 2025State Space Models are Provably Comparable to Transformers in Dynamic Token Selection
52. ICLR 2025Towards Continuous Reuse of Graph Models via Holistic Memory Diversification
53. ICLR 2025Tuning Frequency Bias of State Space Models
54. ICLR 2025Ultra-Sparse Memory Network
55. ICLR 2025Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues
56. ICLR 2024A 2-Dimensional State Space Layer for Spatial Inductive Bias
57. ICLR 2024AutoChunk: Automated Activation Chunk for Memory-Efficient Deep Learning Inference
58. ICLR 2024Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches
59. ICLR 2024Emergent mechanisms for long timescales depend on training curriculum and affect performance in memory tasks
60. ICLR 2024Inverse Approximation Theory for Nonlinear Recurrent Neural Networks
61. ICLR 2024LMUFormer: Low Complexity Yet Powerful Spiking Model With Legendre Memory Units
62. ICLR 2024Parsing neural dynamics with infinite recurrent switching linear dynamical systems
63. ICLR 2024Robustifying State-space Models for Long Sequences via Approximate Diagonalization
64. ICLR 2024Sufficient conditions for offline reactivation in recurrent neural networks
65. ICLR 2024The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks.
66. ICLR 2023Associative Memory Augmented Asynchronous Spatiotemporal Representation Learning for Event-based Perception
67. ICLR 2023Continuous-time identification of dynamic state-space models by deep subspace encoding
68. ICLR 2023Decision S4: Efficient Sequence-Based RL via State Spaces Layers
69. ICLR 2023Distilling Model Failures as Directions in Latent Space
70. ICLR 2023Encoding Recurrence into Transformers
71. ICLR 2023Hebbian and Gradient-based Plasticity Enables Robust Memory and Rapid Learning in RNNs
72. ICLR 2023How to Train your HIPPO: State Space Models with Generalized Orthogonal Basis Projections
73. ICLR 2023Hungry Hungry Hippos: Towards Language Modeling with State Space Models
74. ICLR 2023Incremental Learning of Structured Memory via Closed-Loop Transcription
75. ICLR 2023Learning Low Dimensional State Spaces with Overparameterized Recurrent Neural Nets
76. ICLR 2023Learning to Solve Constraint Satisfaction Problems with Recurrent Transformer
77. ICLR 2023Learning with Auxiliary Activation for Memory-Efficient Training
78. ICLR 2023Liquid Structural State-Space Models
79. ICLR 2023Memory Gym: Partially Observable Challenges to Memory-Based Agents
80. ICLR 2023Neural Networks and the Chomsky Hierarchy
81. ICLR 2023Simplicial Hopfield networks
82. ICLR 2023Value Memory Graph: A Graph-Structured World Model for Offline 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。