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 61 篇，第 1 / 2 页

1. NeurIPS 2025Bridging Expressivity and Scalability with Adaptive Unitary SSMs
2. NeurIPS 2025Computation and Memory-Efficient Model Compression with Gradient Reweighting
3. NeurIPS 2025Cost-Efficient LLM Training with Lifetime-Aware Tensor Offloading via GPUDirect Storage
4. NeurIPS 2025Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation
5. NeurIPS 2025DeltaFormer: Unlock the state space of Transformer
6. NeurIPS 2025DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products
7. NeurIPS 2025DERD-Net: Learning Depth from Event-based Ray Densities
8. NeurIPS 2025DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs
9. NeurIPS 2025DyMoDreamer: World Modeling with Dynamic Modulation
10. NeurIPS 2025Efficient Allocation of Working Memory Resource for Utility Maximization in Humans and Recurrent Neural Networks
11. NeurIPS 2025Error Forcing in Recurrent Neural Networks
12. NeurIPS 2025Exponential Dynamic Energy Network for High Capacity Sequence Memory
13. NeurIPS 2025Fixed-Point RNNs: Interpolating from Diagonal to Dense
14. NeurIPS 2025FLAME: Fast Long-context Adaptive Memory for Event-based Vision
15. NeurIPS 2025Flow Equivariant Recurrent Neural Networks
16. NeurIPS 2025FRN: Fractal-Based Recursive Spectral Reconstruction Network
17. NeurIPS 2025Hankel Singular Value Regularization for Highly Compressible State Space Models
18. NeurIPS 2025Hardware-aligned Hierarchical Sparse Attention for Efficient Long-term Memory Access
19. NeurIPS 2025Inference of Whole Brain Electrophysiological Networks Through Multimodal Integration of Simultaneous Scalp and Intracranial EEG
20. NeurIPS 2025Inference-time Alignment in Continuous Space
21. NeurIPS 2025Irrational Complex Rotations Empower Low-bit Optimizers
22. NeurIPS 2025Kinaema: a recurrent sequence model for memory and pose in motion
23. NeurIPS 2025L$^2$M: Mutual Information Scaling Law for Long-Context Language Modeling
24. NeurIPS 2025Learning Memory-Enhanced Improvement Heuristics for Flexible Job Shop Scheduling
25. NeurIPS 2025Mamba Modulation: On the Length Generalization of Mamba Models
26. NeurIPS 2025Measuring and Controlling Solution Degeneracy across Task-Trained Recurrent Neural Networks
27. NeurIPS 2025Memo: Training Memory-Efficient Embodied Agents with Reinforcement Learning
28. NeurIPS 2025Memory by accident: a theory of learning as a byproduct of network stabilization
29. NeurIPS 2025Memory Mosaics at scale
30. NeurIPS 2025Memory-Augmented Potential Field Theory: A Framework for Adaptive Control in Non-Convex Domains
31. NeurIPS 2025Memory-Enhanced Neural Solvers for Routing Problems
32. NeurIPS 2025Metric Automata Theory: A Unifying Theory of RNNs
33. NeurIPS 2025Nested Learning: The Illusion of Deep Learning Architectures
34. NeurIPS 2025Nonparametric Quantile Regression with ReLU-Activated Recurrent Neural Networks
35. NeurIPS 2025On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learning
36. NeurIPS 2025Overcoming Long Context Limitations of State Space Models via Context Dependent Sparse Attention
37. NeurIPS 2025PASS: Path-selective State Space Model for Event-based Recognition
38. NeurIPS 2025Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory
39. NeurIPS 2025Predictability Enables Parallelization of Nonlinear State Space Models
40. NeurIPS 2025Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs
41. NeurIPS 2025Recurrent Memory for Online Interdomain Gaussian Processes
42. NeurIPS 2025Recurrent Self-Attention Dynamics: An Energy-Agnostic Perspective from Jacobians
43. NeurIPS 2025Revisiting Bi-Linear State Transitions in Recurrent Neural Networks
44. NeurIPS 2025Revisiting Glorot Initialization for Long-Range Linear Recurrences
45. NeurIPS 2025Robust Ego-Exo Correspondence with Long-Term Memory
46. NeurIPS 2025Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection
47. NeurIPS 2025Scaling Up Liquid-Resistance Liquid-Capacitance Networks for Efficient Sequence Modeling
48. NeurIPS 2025Scaling Up Parameter Generation: A Recurrent Diffusion Approach
49. NeurIPS 2025Shaping Sequence Attractor Schema in Recurrent Neural Networks
50. NeurIPS 2025Skill-Driven Neurosymbolic State Abstractions

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。