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 8 / 9 页

  1. NeurIPS 2024Predictive Attractor Models
  2. NeurIPS 2024Provable Benefits of Complex Parameterizations for Structured State Space Models
  3. NeurIPS 2024Recurrent neural networks: vanishing and exploding gradients are not the end of the story
  4. NeurIPS 2024Recurrent Reinforcement Learning with Memoroids
  5. NeurIPS 2024Rethinking Memory and Communication Costs for Efficient Data Parallel Training of Large Language Models
  6. NeurIPS 2024Samba: Severity-aware Recurrent Modeling for Cross-domain Medical Image Grading
  7. NeurIPS 2024Second-order forward-mode optimization of recurrent neural networks for neuroscience
  8. NeurIPS 2024Separations in the Representational Capabilities of Transformers and Recurrent Architectures
  9. NeurIPS 2024START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation
  10. NeurIPS 2024State Space Models on Temporal Graphs: A First-Principles Study
  11. NeurIPS 2024Structured flexibility in recurrent neural networks via neuromodulation
  12. NeurIPS 2024The Expressive Capacity of State Space Models: A Formal Language Perspective
  13. NeurIPS 2024Theoretical Foundations of Deep Selective State-Space Models
  14. NeurIPS 2024Thinking Forward: Memory-Efficient Federated Finetuning of Language Models
  15. NeurIPS 2024Time Makes Space: Emergence of Place Fields in Networks Encoding Temporally Continuous Sensory Experiences
  16. NeurIPS 2024Trading Place for Space: Increasing Location Resolution Reduces Contextual Capacity in Hippocampal Codes
  17. NeurIPS 2024Transformers Can Do Arithmetic with the Right Embeddings
  18. NeurIPS 2024Unconditional stability of a recurrent neural circuit implementing divisive normalization
  19. NeurIPS 2024Understanding the Differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks
  20. NeurIPS 2024VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections
  21. NeurIPS 2024xLSTM: Extended Long Short-Term Memory
  22. CVPR 2023Bilateral Memory Consolidation for Continual Learning
  23. CVPR 2023Color Backdoor: A Robust Poisoning Attack in Color Space
  24. CVPR 2023Continual Semantic Segmentation With Automatic Memory Sample Selection
  25. CVPR 2023Discriminating Known From Unknown Objects via Structure-Enhanced Recurrent Variational AutoEncoder
  26. CVPR 2023Efficient Movie Scene Detection Using State-Space Transformers
  27. CVPR 2023Finding Geometric Models by Clustering in the Consensus Space
  28. CVPR 2023Memory-Friendly Scalable Super-Resolution via Rewinding Lottery Ticket Hypothesis
  29. CVPR 2023NaQ: Leveraging Narrations As Queries To Supervise Episodic Memory
  30. CVPR 2023Restoration of Hand-Drawn Architectural Drawings Using Latent Space Mapping With Degradation Generator
  31. CVPR 2023RIAV-MVS: Recurrent-Indexing an Asymmetric Volume for Multi-View Stereo
  32. CVPR 2023SCADE: NeRFs from Space Carving With Ambiguity-Aware Depth Estimates
  33. CVPR 2023Shape-Constraint Recurrent Flow for 6D Object Pose Estimation
  34. ICLR 2023Associative Memory Augmented Asynchronous Spatiotemporal Representation Learning for Event-based Perception
  35. ICLR 2023Continuous-time identification of dynamic state-space models by deep subspace encoding
  36. ICLR 2023Decision S4: Efficient Sequence-Based RL via State Spaces Layers
  37. ICLR 2023Distilling Model Failures as Directions in Latent Space
  38. ICLR 2023Encoding Recurrence into Transformers
  39. ICLR 2023Hebbian and Gradient-based Plasticity Enables Robust Memory and Rapid Learning in RNNs
  40. ICLR 2023How to Train your HIPPO: State Space Models with Generalized Orthogonal Basis Projections
  41. ICLR 2023Hungry Hungry Hippos: Towards Language Modeling with State Space Models
  42. ICLR 2023Incremental Learning of Structured Memory via Closed-Loop Transcription
  43. ICLR 2023Learning Low Dimensional State Spaces with Overparameterized Recurrent Neural Nets
  44. ICLR 2023Learning to Solve Constraint Satisfaction Problems with Recurrent Transformer
  45. ICLR 2023Learning with Auxiliary Activation for Memory-Efficient Training
  46. ICLR 2023Liquid Structural State-Space Models
  47. ICLR 2023Memory Gym: Partially Observable Challenges to Memory-Based Agents
  48. ICLR 2023Neural Networks and the Chomsky Hierarchy
  49. ICLR 2023Simplicial Hopfield networks
  50. ICLR 2023Value Memory Graph: A Graph-Structured World Model for Offline Reinforcement Learning

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