循环记忆论文趋势 2023–2026
状态空间记忆
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 416 篇被归入该主题的论文。
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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 9 | 17 | 7 | 12 | 45 |
| 2024 | 43 | 10 | 20 | 9 | 82 |
| 2025 | 61 | 20 | 16 | 20 | 117 |
| 2026 | 73 | 35 | 43 | 21 | 172 |
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 73 篇，第 2 / 2 页
- NeurIPS 2026PatchKV: Weight Space Compensation of KV Cache
- NeurIPS 2026PDE-SSM: A Spectral State Space Approach to Spatial Mixing in Diffusion Transformers
- NeurIPS 2026PREPING: Building Agent Memory without Tasks
- NeurIPS 2026Prospective Coding Improves Learning in Deep Continuous-Time Recurrent Networks
- NeurIPS 2026Raven: High-Recall Sequence Modeling via Sparse Memory Routing
- NeurIPS 2026RecMem: Recurrent Memory Compression for Long-Sequence Recommendation
- NeurIPS 2026Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory
- NeurIPS 2026Rethinking State Tracking in Recurrent Models Through Error Control Dynamics
- NeurIPS 2026Rethinking the State Update Gate for Long-Sequence Recurrent 3D Reconstruction
- NeurIPS 2026Selectivity Makes State-Space Models Universal Sequence Approximators
- NeurIPS 2026Skipping Domain Shifts: Domain Memory Retention Enhanced Hyperspectral Single-Source Domain Generalization
- NeurIPS 2026SLVMBench: Skill Learning from Video Memory
- NeurIPS 2026Space Group Conditional Flow Matching
- NeurIPS 2026Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity
- NeurIPS 2026Spectral Quantum Memory for Implicit Neural Representations
- NeurIPS 2026SpikeSSL: A Universal Spike Inference Framework with Dynamics-Informed State-Space Layers
- NeurIPS 2026State Augmented Flows
- NeurIPS 2026Statistical Mixing Guarantees for Contractive Echo State Networks
- NeurIPS 2026StreamPhy: Streaming Inference of High-Dimensional Physical Dynamics via State Space Models
- NeurIPS 2026Structured Sparse Memory for Recurrent Reasoning
- NeurIPS 2026Swimba: Switch Mamba Model Scales State Space Models
- NeurIPS 2026The State-Prediction Separation Hypothesis
- NeurIPS 2026TIDES: Implicit Time-Awareness in Selective State Space Models
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查循环记忆在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "recurrent-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。