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 69 篇，第 1 / 2 页

  1. CVPR 2024BrainWash: A Poisoning Attack to Forget in Continual Learning
  2. CVPR 2024Consistent Prompting for Rehearsal-Free Continual Learning
  3. CVPR 2024Continual Forgetting for Pre-trained Vision Models
  4. CVPR 2024Continual Learning for Motion Prediction Model via Meta-Representation Learning and Optimal Memory Buffer Retention Strategy
  5. CVPR 2024Continual Segmentation with Disentangled Objectness Learning and Class Recognition
  6. CVPR 2024Continual Self-supervised Learning: Towards Universal Multi-modal Medical Data Representation Learning
  7. CVPR 2024Convolutional Prompting meets Language Models for Continual Learning
  8. CVPR 2024Defense without Forgetting: Continual Adversarial Defense with Anisotropic & Isotropic Pseudo Replay
  9. CVPR 2024ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning
  10. CVPR 2024Enhancing Visual Continual Learning with Language-Guided Supervision
  11. CVPR 2024Improving Plasticity in Online Continual Learning via Collaborative Learning
  12. CVPR 2024Learning Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification
  13. CVPR 2024Learning Equi-angular Representations for Online Continual Learning
  14. CVPR 2024RCL: Reliable Continual Learning for Unified Failure Detection
  15. CVPR 2024Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning
  16. CVPR 2024Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer
  17. CVPR 2024Towards Backward-Compatible Continual Learning of Image Compression
  18. CVPR 2024Traceable Federated Continual Learning
  19. ICLR 2024A Probabilistic Framework for Modular Continual Learning
  20. ICLR 2024Accurate Forgetting for Heterogeneous Federated Continual Learning
  21. ICLR 2024Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning
  22. ICLR 2024Continual Learning in the Presence of Spurious Correlations: Analyses and a Simple Baseline
  23. ICLR 2024Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation
  24. ICLR 2024Continual Momentum Filtering on Parameter Space for Online Test-time Adaptation
  25. ICLR 2024Efficient Continual Finite-Sum Minimization
  26. ICLR 2024Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning
  27. ICLR 2024Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks
  28. ICLR 2024Meta Continual Learning Revisited: Implicitly Enhancing Online Hessian Approximation via Variance Reduction
  29. ICLR 2024Prompt Gradient Projection for Continual Learning
  30. ICLR 2024Scalable Language Model with Generalized Continual Learning
  31. ICLR 2024The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting — An Analytical Model
  32. ICLR 2024TiC-CLIP: Continual Training of CLIP Models
  33. ICML 2024An Effective Dynamic Gradient Calibration Method for Continual Learning
  34. ICML 2024COPAL: Continual Pruning in Large Language Generative Models
  35. ICML 2024Disentangled Continual Graph Neural Architecture Search with Invariant Modular Supernet
  36. ICML 2024Forget Sharpness: Perturbed Forgetting of Model Biases Within SAM Dynamics
  37. ICML 2024Layerwise Proximal Replay: A Proximal Point Method for Online Continual Learning
  38. ICML 2024Mitigating Catastrophic Forgetting in Online Continual Learning by Modeling Previous Task Interrelations via Pareto Optimization
  39. ICML 2024On the Diminishing Returns of Width for Continual Learning
  40. ICML 2024One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning
  41. ICML 2024Provable Contrastive Continual Learning
  42. ICML 2024Rapid Learning without Catastrophic Forgetting in the Morris Water Maze
  43. ICML 2024Regularizing with Pseudo-Negatives for Continual Self-Supervised Learning
  44. ICML 2024Self-Composing Policies for Scalable Continual Reinforcement Learning
  45. ICML 2024Task-aware Orthogonal Sparse Network for Exploring Shared Knowledge in Continual Learning
  46. ICML 2024Understanding Forgetting in Continual Learning with Linear Regression
  47. NeurIPS 2024A Topology-aware Graph Coarsening Framework for Continual Graph Learning
  48. NeurIPS 2024CoIN: A Benchmark of Continual Instruction Tuning for Multimodel Large Language Models
  49. NeurIPS 2024Continual Learning in the Frequency Domain
  50. NeurIPS 2024Continual Learning with Global Alignment

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