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 186 篇，第 1 / 4 页

1. NeurIPS 2026A dynamical systems theory of reward-modulated learning in linear recurrent networks
2. NeurIPS 2026A Hebbian Recurrent Neural Network Explains the Hierarchical Geometry of Sequence Memory
3. NeurIPS 2026Approximate Memory Suffices for Universal Approximation with State Space Models
4. NeurIPS 2026Attend Locally, Remember Linearly: Linear Attention as Cross-Frame Memory for Autoregressive Video Diffusion
5. NeurIPS 2026Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks
6. NeurIPS 2026C3: Long-Horizon Character Consistency via Causal-Continuous State Dynamics and Memory Rewriting
7. NeurIPS 2026Commutator Memory: Sparse, Path-Local Reading and Steering in Language Models
8. NeurIPS 2026Consistent 3D Surface Flow Model with Global State
9. NeurIPS 2026Context as Low-Rank Weights: Bounded Parametric Dynamic Memory for Unbounded Context
10. NeurIPS 2026Cortically-Resolved Recurrent Architecture for fMRI
11. NeurIPS 2026Depth-Recurrent Attention Mixtures: Giving Latent Reasoning the Attention it Deserves
12. NeurIPS 2026Dynamic Optimistic Constrained OCO with Memory via Delay Equivalence
13. NeurIPS 2026FacePhys: State of the Heart Learning
14. NeurIPS 2026Fault Tolerance in Transformers Favors Output Alignment over Hidden-State Consistency
15. NeurIPS 2026Flow-Guided Target-Space Alignment via Path Consistency
16. NeurIPS 2026Foveal-Mamba: Inside-Out Ring Scanning with Recurrent Offset Prediction for Visual State Space Models
17. NeurIPS 2026Fractional State Space Transition for Long Sequence Modeling
18. NeurIPS 2026FrameVGGT: Coherence-Preserving Memory for Bounded Streaming Geometry
19. NeurIPS 2026Free energy Estimation on Any State Space
20. NeurIPS 2026FRInGe: Distribution-Space Integrated Gradients with Fisher–Rao Geometry
21. NeurIPS 2026From sequences to schemas: low-rank recurrent dynamics underlie abstract relational representations
22. NeurIPS 2026GEAR: Generator-Adaptive State Space Models for Associative Recall
23. NeurIPS 2026GeoMamba: Geometry-Aware State Space Modeling for Image Restoration
24. NeurIPS 2026GPU Hierarchy Meets Structured Matrices: Fast Algorithms for State-Space Models
25. NeurIPS 2026HaM-World: Soft-Hamiltonian World Models with Selective Memory for Planning
26. NeurIPS 2026HeMeR: Heterogeneous Memory Reconciliation for Embodied Agents via Structured KV Reuse
27. NeurIPS 2026Hit Expansion via Localized Exploration of Synthesizable Chemical Space
28. NeurIPS 2026How does feature learning change the function space evolution?
29. NeurIPS 2026Improved State Mixing in Higher-order and Block Diagonal Linear Recurrent Networks
30. NeurIPS 2026Improved Weakly Supervised Semantic Segmentation with A Relationally Optimized Prototype Memory Bank Framework
31. NeurIPS 2026Inferring how internal brain state shapes neural responses with state-dependent diffusion models
32. NeurIPS 2026Learning interpretable Schur forms of recurrent weight matrices
33. NeurIPS 2026Learning Interpretable Switching Dynamics in Shared Neural-Behavioral Latent Space
34. NeurIPS 2026Leveraging Dale’s Principle as an Inductive Bias in Recurrent Neural Networks
35. NeurIPS 2026LinearARD: Linear-Memory Attention Distillation for RoPE Restoration
36. NeurIPS 2026LogSig-SSM: Time-Series Modelling with Multi-Scale Log-Signature Compression for State-Space Models
37. NeurIPS 2026Loss is Not Behavior: A Unified Output-Space Analysis of Gradient-Based Machine Unlearning
38. NeurIPS 2026MaRK: Markov-adapted Recurrent Kernels for Dynamic Operator Conditioning in State Space Models
39. NeurIPS 2026MemDLM: Memory-Enhanced DLM Training
40. NeurIPS 2026Memory Determines Learning Direction: A Theory of Gradient-Based Optimization in State Space Models
41. NeurIPS 2026Memory Inception: Latent-Space KV Cache Manipulation for Steering LLMs
42. NeurIPS 2026Memory-Driven Contrastive Embedding Enhancement for Fine-Grained Open-Set Semi-Supervised Learning
43. NeurIPS 2026MemoryFusion: Cross-Temporal Memory Learning for Multimodal Video Fusion
44. NeurIPS 2026MemReg: Streaming Outdoor LiDAR Point Cloud Registration with Hybrid Memory Buffers
45. NeurIPS 2026MESSENGER: Memory-Enhanced Sequential Scene Flow Estimation via Autoregressive Next-Frame Forecasting
46. NeurIPS 2026MinMax Recurrent Neural Cascades
47. NeurIPS 2026MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse Lookup
48. NeurIPS 2026MoSE3: Learning World-Space SE(3) at Every Pixel
49. NeurIPS 2026NASDAQ: Normalized Observation Space Dynamics-Augmented Q-Learning
50. NeurIPS 2026On the Importance of Gating: Memorization vs. In-Context Learning in State Space 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。