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

每年论文数

各会议论文数

按年份和会议统计

循环记忆论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202391771245
2024431020982
202561201620117
202673354321172

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

全部循环记忆论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 186 篇，第 3 / 4 页

  1. NeurIPS 2025Memory by accident: a theory of learning as a byproduct of network stabilization
  2. NeurIPS 2025Memory Mosaics at scale
  3. NeurIPS 2025Memory-Augmented Potential Field Theory: A Framework for Adaptive Control in Non-Convex Domains
  4. NeurIPS 2025Memory-Enhanced Neural Solvers for Routing Problems
  5. NeurIPS 2025Metric Automata Theory: A Unifying Theory of RNNs
  6. NeurIPS 2025Nested Learning: The Illusion of Deep Learning Architectures
  7. NeurIPS 2025Nonparametric Quantile Regression with ReLU-Activated Recurrent Neural Networks
  8. NeurIPS 2025On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learning
  9. NeurIPS 2025Overcoming Long Context Limitations of State Space Models via Context Dependent Sparse Attention
  10. NeurIPS 2025PASS: Path-selective State Space Model for Event-based Recognition
  11. NeurIPS 2025Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory
  12. NeurIPS 2025Predictability Enables Parallelization of Nonlinear State Space Models
  13. NeurIPS 2025Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs
  14. NeurIPS 2025Recurrent Memory for Online Interdomain Gaussian Processes
  15. NeurIPS 2025Recurrent Self-Attention Dynamics: An Energy-Agnostic Perspective from Jacobians
  16. NeurIPS 2025Revisiting Bi-Linear State Transitions in Recurrent Neural Networks
  17. NeurIPS 2025Revisiting Glorot Initialization for Long-Range Linear Recurrences
  18. NeurIPS 2025Robust Ego-Exo Correspondence with Long-Term Memory
  19. NeurIPS 2025Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection
  20. NeurIPS 2025Scaling Up Liquid-Resistance Liquid-Capacitance Networks for Efficient Sequence Modeling
  21. NeurIPS 2025Scaling Up Parameter Generation: A Recurrent Diffusion Approach
  22. NeurIPS 2025Shaping Sequence Attractor Schema in Recurrent Neural Networks
  23. NeurIPS 2025Skill-Driven Neurosymbolic State Abstractions
  24. NeurIPS 2025Slow Transition to Low-Dimensional Chaos in Heavy-Tailed Recurrent Neural Networks
  25. NeurIPS 2025SpectraLDS: Provable Distillation for Linear Dynamical Systems
  26. NeurIPS 2025Steering Information Utility in Key-Value Memory for Language Model Post-Training
  27. NeurIPS 2025STree: Speculative Tree Decoding for Hybrid State Space Models
  28. NeurIPS 2025Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models
  29. NeurIPS 2025Task-Optimized Convolutional Recurrent Networks Align with Tactile Processing in the Rodent Brain
  30. NeurIPS 2025The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels
  31. NeurIPS 2025Uncovering the Spectral Bias in Diagonal State Space Models
  32. NeurIPS 2025Unfolding the Black Box of Recurrent Neural Networks for Path Integration
  33. NeurIPS 2025WaLRUS: Wavelets for Long range Representation Using State Space Methods
  34. NeurIPS 2025xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories
  35. NeurIPS 2024Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective
  36. NeurIPS 2024B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory
  37. NeurIPS 2024Controlled maximal variability along with reliable performance in recurrent neural networks
  38. NeurIPS 2024Coupled Mamba: Enhanced Multimodal Fusion with Coupled State Space Model
  39. NeurIPS 2024Critically Assessing the State of the Art in Neural Network Verification
  40. NeurIPS 2024ECMamba: Consolidating Selective State Space Model with Retinex Guidance for Efficient Multiple Exposure Correction
  41. NeurIPS 2024Expanding Sparse Tuning for Low Memory Usage
  42. NeurIPS 2024Exploring Adversarial Robustness of Deep State Space Models
  43. NeurIPS 2024Feedback control guides credit assignment in recurrent neural networks
  44. NeurIPS 2024Gated Inference Network: Inference and Learning State-Space Models
  45. NeurIPS 2024Geometry of naturalistic object representations in recurrent neural network models of working memory
  46. NeurIPS 2024Global Distortions from Local Rewards: Neural Coding Strategies in Path-Integrating Neural Systems
  47. NeurIPS 2024Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers
  48. NeurIPS 2024Inference of Neural Dynamics Using Switching Recurrent Neural Networks
  49. NeurIPS 2024MambaLRP: Explaining Selective State Space Sequence Models
  50. NeurIPS 2024Memory-Efficient LLM Training with Online Subspace Descent

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"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「长上下文与记忆」下的其他主题