循环记忆论文趋势 2023–2026

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。

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 117 篇，第 1 / 3 页

1. CVPR 2025Breaking the Memory Barrier of Contrastive Loss via Tile-Based Strategy
2. CVPR 2025Continuous 3D Perception Model with Persistent State
3. CVPR 2025DefMamba: Deformable Visual State Space Model
4. CVPR 2025EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality
5. CVPR 2025Enhancing Online Continual Learning with Plug-and-Play State Space Model and Class-Conditional Mixture of Discretization
6. CVPR 2025Event-based Video Super-Resolution via State Space Models
7. CVPR 2025Exploiting Temporal State Space Sharing for Video Semantic Segmentation
8. CVPR 2025GG-SSMs: Graph-Generating State Space Models
9. CVPR 2025Latent Space Imaging
10. CVPR 2025Learning Phase Distortion with Selective State Space Models for Video Turbulence Mitigation
11. CVPR 2025M3amba: Memory Mamba is All You Need for Whole Slide Image Classification
12. CVPR 2025Making Old Film Great Again: Degradation-aware State Space Model for Old Film Restoration
13. CVPR 2025Mamba-Adaptor: State Space Model Adaptor for Visual Recognition
14. CVPR 2025MambaIRv2: Attentive State Space Restoration
15. CVPR 2025MEET: Towards Memory-Efficient Temporal Sparse Deep Neural Networks
16. CVPR 2025OccMamba: Semantic Occupancy Prediction with State Space Models
17. CVPR 2025Online Task-Free Continual Learning via Dynamic Expansionable Memory Distribution
18. CVPR 2025QMambaBSR: Burst Image Super-Resolution with Query State Space Model
19. CVPR 2025Simpler Diffusion: 1.5 FID on ImageNet512 with Pixel-space Diffusion
20. CVPR 2025Stochastic Human Motion Prediction with Memory of Action Transition and Action Characteristic
21. ICLR 2025Associative memory and dead neurons
22. ICLR 2025Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space Models
23. ICLR 2025Demystifying the Token Dynamics of Deep Selective State Space Models
24. ICLR 2025Exploring channel distinguishability in local neighborhoods of the model space in quantum neural networks
25. ICLR 2025From Layers to States: A State Space Model Perspective to Deep Neural Network Layer Dynamics
26. ICLR 2025Gated Delta Networks: Improving Mamba2 with Delta Rule
27. ICLR 2025HOPE for a Robust Parameterization of Long-memory State Space Models
28. ICLR 2025Jamba: Hybrid Transformer-Mamba Language Models
29. ICLR 2025Lipschitz Bandits in Optimal Space
30. ICLR 2025Locally Connected Echo State Networks for Time Series Forecasting
31. ICLR 2025MIRACLE 3D: Memory-efficient Integrated Robust Approach for Continual Learning on 3D Point Clouds via Shape Model Construction
32. ICLR 2025On the Benefits of Memory for Modeling Time-Dependent PDEs
33. ICLR 2025Oscillatory State-Space Models
34. ICLR 2025Quamba: A Post-Training Quantization Recipe for Selective State Space Models
35. ICLR 2025Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
36. ICLR 2025State Space Models are Provably Comparable to Transformers in Dynamic Token Selection
37. ICLR 2025Towards Continuous Reuse of Graph Models via Holistic Memory Diversification
38. ICLR 2025Tuning Frequency Bias of State Space Models
39. ICLR 2025Ultra-Sparse Memory Network
40. ICLR 2025Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues
41. ICML 2025Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity
42. ICML 2025Dynamical phases of short-term memory mechanisms in RNNs
43. ICML 2025Flow-field inference from neural data using deep recurrent networks
44. ICML 2025From Weight-Based to State-Based Fine-Tuning: Further Memory Reduction on LoRA with Parallel Control
45. ICML 2025FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training
46. ICML 2025Identifying Neural Dynamics Using Interventional State Space Models
47. ICML 2025Learning dynamics in linear recurrent neural networks
48. ICML 2025Lego Sketch: A Scalable Memory-augmented Neural Network for Sketching Data Streams
49. ICML 2025Liger: Linearizing Large Language Models to Gated Recurrent Structures
50. ICML 2025Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models

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。