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. NeurIPS 2024Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective
2. NeurIPS 2024B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory
3. NeurIPS 2024Controlled maximal variability along with reliable performance in recurrent neural networks
4. NeurIPS 2024Coupled Mamba: Enhanced Multimodal Fusion with Coupled State Space Model
5. NeurIPS 2024Critically Assessing the State of the Art in Neural Network Verification
6. NeurIPS 2024ECMamba: Consolidating Selective State Space Model with Retinex Guidance for Efficient Multiple Exposure Correction
7. NeurIPS 2024Expanding Sparse Tuning for Low Memory Usage
8. NeurIPS 2024Exploring Adversarial Robustness of Deep State Space Models
9. NeurIPS 2024Feedback control guides credit assignment in recurrent neural networks
10. NeurIPS 2024Gated Inference Network: Inference and Learning State-Space Models
11. NeurIPS 2024Geometry of naturalistic object representations in recurrent neural network models of working memory
12. NeurIPS 2024Global Distortions from Local Rewards: Neural Coding Strategies in Path-Integrating Neural Systems
13. NeurIPS 2024Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers
14. NeurIPS 2024Inference of Neural Dynamics Using Switching Recurrent Neural Networks
15. NeurIPS 2024MambaLRP: Explaining Selective State Space Sequence Models
16. NeurIPS 2024Memory-Efficient LLM Training with Online Subspace Descent
17. NeurIPS 2024Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy
18. NeurIPS 2024Navigating Extremes: Dynamic Sparsity in Large Output Spaces
19. NeurIPS 2024Not so griddy: Internal representations of RNNs path integrating more than one agent
20. NeurIPS 2024On Feature Learning in Structured State Space Models
21. NeurIPS 2024Parallelizing Linear Transformers with the Delta Rule over Sequence Length
22. NeurIPS 2024PointMamba: A Simple State Space Model for Point Cloud Analysis
23. NeurIPS 2024Predictive Attractor Models
24. NeurIPS 2024Provable Benefits of Complex Parameterizations for Structured State Space Models
25. NeurIPS 2024Recurrent neural networks: vanishing and exploding gradients are not the end of the story
26. NeurIPS 2024Recurrent Reinforcement Learning with Memoroids
27. NeurIPS 2024Rethinking Memory and Communication Costs for Efficient Data Parallel Training of Large Language Models
28. NeurIPS 2024Samba: Severity-aware Recurrent Modeling for Cross-domain Medical Image Grading
29. NeurIPS 2024Second-order forward-mode optimization of recurrent neural networks for neuroscience
30. NeurIPS 2024Separations in the Representational Capabilities of Transformers and Recurrent Architectures
31. NeurIPS 2024START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation
32. NeurIPS 2024State Space Models on Temporal Graphs: A First-Principles Study
33. NeurIPS 2024Structured flexibility in recurrent neural networks via neuromodulation
34. NeurIPS 2024The Expressive Capacity of State Space Models: A Formal Language Perspective
35. NeurIPS 2024Theoretical Foundations of Deep Selective State-Space Models
36. NeurIPS 2024Thinking Forward: Memory-Efficient Federated Finetuning of Language Models
37. NeurIPS 2024Time Makes Space: Emergence of Place Fields in Networks Encoding Temporally Continuous Sensory Experiences
38. NeurIPS 2024Trading Place for Space: Increasing Location Resolution Reduces Contextual Capacity in Hippocampal Codes
39. NeurIPS 2024Transformers Can Do Arithmetic with the Right Embeddings
40. NeurIPS 2024Unconditional stability of a recurrent neural circuit implementing divisive normalization
41. NeurIPS 2024Understanding the Differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks
42. NeurIPS 2024VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections
43. NeurIPS 2024xLSTM: Extended Long Short-Term 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。