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 416 篇，第 4 / 9 页

  1. NeurIPS 2026PDE-SSM: A Spectral State Space Approach to Spatial Mixing in Diffusion Transformers
  2. NeurIPS 2026PREPING: Building Agent Memory without Tasks
  3. NeurIPS 2026Prospective Coding Improves Learning in Deep Continuous-Time Recurrent Networks
  4. NeurIPS 2026Raven: High-Recall Sequence Modeling via Sparse Memory Routing
  5. NeurIPS 2026RecMem: Recurrent Memory Compression for Long-Sequence Recommendation
  6. NeurIPS 2026Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory
  7. NeurIPS 2026Rethinking State Tracking in Recurrent Models Through Error Control Dynamics
  8. NeurIPS 2026Rethinking the State Update Gate for Long-Sequence Recurrent 3D Reconstruction
  9. NeurIPS 2026Selectivity Makes State-Space Models Universal Sequence Approximators
  10. NeurIPS 2026Skipping Domain Shifts: Domain Memory Retention Enhanced Hyperspectral Single-Source Domain Generalization
  11. NeurIPS 2026SLVMBench: Skill Learning from Video Memory
  12. NeurIPS 2026Space Group Conditional Flow Matching
  13. NeurIPS 2026Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity
  14. NeurIPS 2026Spectral Quantum Memory for Implicit Neural Representations
  15. NeurIPS 2026SpikeSSL: A Universal Spike Inference Framework with Dynamics-Informed State-Space Layers
  16. NeurIPS 2026State Augmented Flows
  17. NeurIPS 2026Statistical Mixing Guarantees for Contractive Echo State Networks
  18. NeurIPS 2026StreamPhy: Streaming Inference of High-Dimensional Physical Dynamics via State Space Models
  19. NeurIPS 2026Structured Sparse Memory for Recurrent Reasoning
  20. NeurIPS 2026Swimba: Switch Mamba Model Scales State Space Models
  21. NeurIPS 2026The State-Prediction Separation Hypothesis
  22. NeurIPS 2026TIDES: Implicit Time-Awareness in Selective State Space Models
  23. CVPR 2025Breaking the Memory Barrier of Contrastive Loss via Tile-Based Strategy
  24. CVPR 2025Continuous 3D Perception Model with Persistent State
  25. CVPR 2025DefMamba: Deformable Visual State Space Model
  26. CVPR 2025EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality
  27. CVPR 2025Enhancing Online Continual Learning with Plug-and-Play State Space Model and Class-Conditional Mixture of Discretization
  28. CVPR 2025Event-based Video Super-Resolution via State Space Models
  29. CVPR 2025Exploiting Temporal State Space Sharing for Video Semantic Segmentation
  30. CVPR 2025GG-SSMs: Graph-Generating State Space Models
  31. CVPR 2025Latent Space Imaging
  32. CVPR 2025Learning Phase Distortion with Selective State Space Models for Video Turbulence Mitigation
  33. CVPR 2025M3amba: Memory Mamba is All You Need for Whole Slide Image Classification
  34. CVPR 2025Making Old Film Great Again: Degradation-aware State Space Model for Old Film Restoration
  35. CVPR 2025Mamba-Adaptor: State Space Model Adaptor for Visual Recognition
  36. CVPR 2025MambaIRv2: Attentive State Space Restoration
  37. CVPR 2025MEET: Towards Memory-Efficient Temporal Sparse Deep Neural Networks
  38. CVPR 2025OccMamba: Semantic Occupancy Prediction with State Space Models
  39. CVPR 2025Online Task-Free Continual Learning via Dynamic Expansionable Memory Distribution
  40. CVPR 2025QMambaBSR: Burst Image Super-Resolution with Query State Space Model
  41. CVPR 2025Simpler Diffusion: 1.5 FID on ImageNet512 with Pixel-space Diffusion
  42. CVPR 2025Stochastic Human Motion Prediction with Memory of Action Transition and Action Characteristic
  43. ICLR 2025Associative memory and dead neurons
  44. ICLR 2025Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space Models
  45. ICLR 2025Demystifying the Token Dynamics of Deep Selective State Space Models
  46. ICLR 2025Exploring channel distinguishability in local neighborhoods of the model space in quantum neural networks
  47. ICLR 2025From Layers to States: A State Space Model Perspective to Deep Neural Network Layer Dynamics
  48. ICLR 2025Gated Delta Networks: Improving Mamba2 with Delta Rule
  49. ICLR 2025HOPE for a Robust Parameterization of Long-memory State Space Models
  50. ICLR 2025Jamba: Hybrid Transformer-Mamba Language 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"}

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