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 186 篇，第 4 / 4 页
- NeurIPS 2024Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy
- NeurIPS 2024Navigating Extremes: Dynamic Sparsity in Large Output Spaces
- NeurIPS 2024Not so griddy: Internal representations of RNNs path integrating more than one agent
- NeurIPS 2024On Feature Learning in Structured State Space Models
- NeurIPS 2024Parallelizing Linear Transformers with the Delta Rule over Sequence Length
- NeurIPS 2024PointMamba: A Simple State Space Model for Point Cloud Analysis
- NeurIPS 2024Predictive Attractor Models
- NeurIPS 2024Provable Benefits of Complex Parameterizations for Structured State Space Models
- NeurIPS 2024Recurrent neural networks: vanishing and exploding gradients are not the end of the story
- NeurIPS 2024Recurrent Reinforcement Learning with Memoroids
- NeurIPS 2024Rethinking Memory and Communication Costs for Efficient Data Parallel Training of Large Language Models
- NeurIPS 2024Samba: Severity-aware Recurrent Modeling for Cross-domain Medical Image Grading
- NeurIPS 2024Second-order forward-mode optimization of recurrent neural networks for neuroscience
- NeurIPS 2024Separations in the Representational Capabilities of Transformers and Recurrent Architectures
- NeurIPS 2024START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation
- NeurIPS 2024State Space Models on Temporal Graphs: A First-Principles Study
- NeurIPS 2024Structured flexibility in recurrent neural networks via neuromodulation
- NeurIPS 2024The Expressive Capacity of State Space Models: A Formal Language Perspective
- NeurIPS 2024Theoretical Foundations of Deep Selective State-Space Models
- NeurIPS 2024Thinking Forward: Memory-Efficient Federated Finetuning of Language Models
- NeurIPS 2024Time Makes Space: Emergence of Place Fields in Networks Encoding Temporally Continuous Sensory Experiences
- NeurIPS 2024Trading Place for Space: Increasing Location Resolution Reduces Contextual Capacity in Hippocampal Codes
- NeurIPS 2024Transformers Can Do Arithmetic with the Right Embeddings
- NeurIPS 2024Unconditional stability of a recurrent neural circuit implementing divisive normalization
- NeurIPS 2024Understanding the Differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks
- NeurIPS 2024VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections
- NeurIPS 2024xLSTM: Extended Long Short-Term Memory
- NeurIPS 2023Deep Equilibrium Based Neural Operators for Steady-State PDEs
- NeurIPS 2023Hypothesis Selection with Memory Constraints
- NeurIPS 2023Long Sequence Hopfield Memory
- NeurIPS 2023MEMTO: Memory-guided Transformer for Multivariate Time Series Anomaly Detection
- NeurIPS 2023On the Role of Noise in the Sample Complexity of Learning Recurrent Neural Networks: Exponential Gaps for Long Sequences
- NeurIPS 2023Recurrent Hypernetworks are Surprisingly Strong in Meta-RL
- NeurIPS 2023Recurrent Temporal Revision Graph Networks
- NeurIPS 2023State-space models with layer-wise nonlinearity are universal approximators with exponential decaying memory
- NeurIPS 2023Transformer as a hippocampal memory consolidation model based on NMDAR-inspired nonlinearity
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。