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 5 / 9 页

  1. ICLR 2025Lipschitz Bandits in Optimal Space
  2. ICLR 2025Locally Connected Echo State Networks for Time Series Forecasting
  3. ICLR 2025MIRACLE 3D: Memory-efficient Integrated Robust Approach for Continual Learning on 3D Point Clouds via Shape Model Construction
  4. ICLR 2025On the Benefits of Memory for Modeling Time-Dependent PDEs
  5. ICLR 2025Oscillatory State-Space Models
  6. ICLR 2025Quamba: A Post-Training Quantization Recipe for Selective State Space Models
  7. ICLR 2025Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
  8. ICLR 2025State Space Models are Provably Comparable to Transformers in Dynamic Token Selection
  9. ICLR 2025Towards Continuous Reuse of Graph Models via Holistic Memory Diversification
  10. ICLR 2025Tuning Frequency Bias of State Space Models
  11. ICLR 2025Ultra-Sparse Memory Network
  12. ICLR 2025Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues
  13. ICML 2025Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity
  14. ICML 2025Dynamical phases of short-term memory mechanisms in RNNs
  15. ICML 2025Flow-field inference from neural data using deep recurrent networks
  16. ICML 2025From Weight-Based to State-Based Fine-Tuning: Further Memory Reduction on LoRA with Parallel Control
  17. ICML 2025FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training
  18. ICML 2025Identifying Neural Dynamics Using Interventional State Space Models
  19. ICML 2025Learning dynamics in linear recurrent neural networks
  20. ICML 2025Lego Sketch: A Scalable Memory-augmented Neural Network for Sketching Data Streams
  21. ICML 2025Liger: Linearizing Large Language Models to Gated Recurrent Structures
  22. ICML 2025Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models
  23. ICML 2025Minerva: A Programmable Memory Test Benchmark for Language Models
  24. ICML 2025Oracle-MoE: Locality-preserving Routing in the Oracle Space for Memory-constrained Large Language Model Inference
  25. ICML 2025Pixel2Feature Attack (P2FA): Rethinking the Perturbed Space to Enhance Adversarial Transferability
  26. ICML 2025Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models
  27. ICML 2025Quantifying Memory Utilization with Effective State-Size
  28. ICML 2025Tensor Decomposition Based Memory-Efficient Incremental Learning
  29. NeurIPS 2025Bridging Expressivity and Scalability with Adaptive Unitary SSMs
  30. NeurIPS 2025Computation and Memory-Efficient Model Compression with Gradient Reweighting
  31. NeurIPS 2025Cost-Efficient LLM Training with Lifetime-Aware Tensor Offloading via GPUDirect Storage
  32. NeurIPS 2025Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation
  33. NeurIPS 2025DeltaFormer: Unlock the state space of Transformer
  34. NeurIPS 2025DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products
  35. NeurIPS 2025DERD-Net: Learning Depth from Event-based Ray Densities
  36. NeurIPS 2025DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs
  37. NeurIPS 2025DyMoDreamer: World Modeling with Dynamic Modulation
  38. NeurIPS 2025Efficient Allocation of Working Memory Resource for Utility Maximization in Humans and Recurrent Neural Networks
  39. NeurIPS 2025Error Forcing in Recurrent Neural Networks
  40. NeurIPS 2025Exponential Dynamic Energy Network for High Capacity Sequence Memory
  41. NeurIPS 2025Fixed-Point RNNs: Interpolating from Diagonal to Dense
  42. NeurIPS 2025FLAME: Fast Long-context Adaptive Memory for Event-based Vision
  43. NeurIPS 2025Flow Equivariant Recurrent Neural Networks
  44. NeurIPS 2025FRN: Fractal-Based Recursive Spectral Reconstruction Network
  45. NeurIPS 2025Hankel Singular Value Regularization for Highly Compressible State Space Models
  46. NeurIPS 2025Hardware-aligned Hierarchical Sparse Attention for Efficient Long-term Memory Access
  47. NeurIPS 2025Inference of Whole Brain Electrophysiological Networks Through Multimodal Integration of Simultaneous Scalp and Intracranial EEG
  48. NeurIPS 2025Inference-time Alignment in Continuous Space
  49. NeurIPS 2025Irrational Complex Rotations Empower Low-bit Optimizers
  50. NeurIPS 2025Kinaema: a recurrent sequence model for memory and pose in motion

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