持续学习论文趋势 2023–2026

灾难性遗忘

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 381 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

持续学习论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
20232713162177
20242314141869
202532232920104
202639284222131

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

全部持续学习论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 381 篇，第 6 / 8 页

  1. CVPR 2024Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer
  2. CVPR 2024Towards Backward-Compatible Continual Learning of Image Compression
  3. CVPR 2024Traceable Federated Continual Learning
  4. ICLR 2024A Probabilistic Framework for Modular Continual Learning
  5. ICLR 2024Accurate Forgetting for Heterogeneous Federated Continual Learning
  6. ICLR 2024Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning
  7. ICLR 2024Continual Learning in the Presence of Spurious Correlations: Analyses and a Simple Baseline
  8. ICLR 2024Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation
  9. ICLR 2024Continual Momentum Filtering on Parameter Space for Online Test-time Adaptation
  10. ICLR 2024Efficient Continual Finite-Sum Minimization
  11. ICLR 2024Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning
  12. ICLR 2024Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks
  13. ICLR 2024Meta Continual Learning Revisited: Implicitly Enhancing Online Hessian Approximation via Variance Reduction
  14. ICLR 2024Prompt Gradient Projection for Continual Learning
  15. ICLR 2024Scalable Language Model with Generalized Continual Learning
  16. ICLR 2024The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting — An Analytical Model
  17. ICLR 2024TiC-CLIP: Continual Training of CLIP Models
  18. ICML 2024An Effective Dynamic Gradient Calibration Method for Continual Learning
  19. ICML 2024COPAL: Continual Pruning in Large Language Generative Models
  20. ICML 2024Disentangled Continual Graph Neural Architecture Search with Invariant Modular Supernet
  21. ICML 2024Forget Sharpness: Perturbed Forgetting of Model Biases Within SAM Dynamics
  22. ICML 2024Layerwise Proximal Replay: A Proximal Point Method for Online Continual Learning
  23. ICML 2024Mitigating Catastrophic Forgetting in Online Continual Learning by Modeling Previous Task Interrelations via Pareto Optimization
  24. ICML 2024On the Diminishing Returns of Width for Continual Learning
  25. ICML 2024One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning
  26. ICML 2024Provable Contrastive Continual Learning
  27. ICML 2024Rapid Learning without Catastrophic Forgetting in the Morris Water Maze
  28. ICML 2024Regularizing with Pseudo-Negatives for Continual Self-Supervised Learning
  29. ICML 2024Self-Composing Policies for Scalable Continual Reinforcement Learning
  30. ICML 2024Task-aware Orthogonal Sparse Network for Exploring Shared Knowledge in Continual Learning
  31. ICML 2024Understanding Forgetting in Continual Learning with Linear Regression
  32. NeurIPS 2024A Topology-aware Graph Coarsening Framework for Continual Graph Learning
  33. NeurIPS 2024CoIN: A Benchmark of Continual Instruction Tuning for Multimodel Large Language Models
  34. NeurIPS 2024Continual Learning in the Frequency Domain
  35. NeurIPS 2024Continual Learning with Global Alignment
  36. NeurIPS 2024Continual learning with the neural tangent ensemble
  37. NeurIPS 2024Disentangling and mitigating the impact of task similarity for continual learning
  38. NeurIPS 2024Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learning
  39. NeurIPS 2024GACL: Exemplar-Free Generalized Analytic Continual Learning
  40. NeurIPS 2024Label Delay in Online Continual Learning
  41. NeurIPS 2024Learn more, but bother less: parameter efficient continual learning
  42. NeurIPS 2024Learning Successor Features the Simple Way
  43. NeurIPS 2024Leveraging Catastrophic Forgetting to Develop Safe Diffusion Models against Malicious Finetuning
  44. NeurIPS 2024Make Continual Learning Stronger via C-Flat
  45. NeurIPS 2024Mixture of Experts Meets Prompt-Based Continual Learning
  46. NeurIPS 2024Model Sensitivity Aware Continual Learning
  47. NeurIPS 2024Parseval Regularization for Continual Reinforcement Learning
  48. NeurIPS 2024Persistence Homology Distillation for Semi-supervised Continual Learning
  49. NeurIPS 2024Reawakening knowledge: Anticipatory recovery from catastrophic interference via structured training
  50. NeurIPS 2024Saliency-driven Experience Replay for Continual 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 查持续学习在 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": "continual-learning"}

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持续学习论文？
共 381 篇，按年份分别是 2023 年 77 篇、2024 年 69 篇、2025 年 104 篇、2026 年 131 篇。
NeurIPS 2026 有多少篇持续学习论文？
NeurIPS 2026 有 39 篇持续学习论文，上一届是 32 篇。
ICLR 2026 有多少篇持续学习论文？
ICLR 2026 有 28 篇持续学习论文，上一届是 23 篇。
ICML 2026 有多少篇持续学习论文？
ICML 2026 有 42 篇持续学习论文，上一届是 29 篇。
CVPR 2026 有多少篇持续学习论文？
CVPR 2026 有 22 篇持续学习论文，上一届是 20 篇。
哪个会议的持续学习论文最多？
NeurIPS，2023–2026 年共 121 篇。

「元学习与迁移」下的其他主题