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 4 / 8 页

  1. CVPR 2025Towards Continual Universal Segmentation
  2. ICLR 2025Active Learning for Continual Learning: Keeping the Past Alive in the Present
  3. ICLR 2025Adapt-$\infty$: Scalable Continual Multimodal Instruction Tuning via Dynamic Data Selection
  4. ICLR 2025Advancing Prompt-Based Methods for Replay-Independent General Continual Learning
  5. ICLR 2025Boosting Multiple Views for pretrained-based Continual Learning
  6. ICLR 2025C-CLIP: Multimodal Continual Learning for Vision-Language Model
  7. ICLR 2025CLDyB: Towards Dynamic Benchmarking for Continual Learning with Pre-trained Models
  8. ICLR 2025Convergence and Implicit Bias of Gradient Descent on Continual Linear Classification
  9. ICLR 2025Coreset Selection via Reducible Loss in Continual Learning
  10. ICLR 2025Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization
  11. ICLR 2025Exploring The Forgetting in Adversarial Training: A Novel Method for Enhancing Robustness
  12. ICLR 2025Federated Continual Learning Goes Online: Uncertainty-Aware Memory Management for Vision Tasks and Beyond
  13. ICLR 2025Last Iterate Convergence of Incremental Methods as a Model of Forgetting
  14. ICLR 2025Learning Continually by Spectral Regularization
  15. ICLR 2025MIRACLE 3D: Memory-efficient Integrated Robust Approach for Continual Learning on 3D Point Clouds via Shape Model Construction
  16. ICLR 2025N-ForGOT: Towards Not-forgetting and Generalization of Open Temporal Graph Learning
  17. ICLR 2025On Large Language Model Continual Unlearning
  18. ICLR 2025Plastic Learning with Deep Fourier Features
  19. ICLR 2025PseDet: Revisiting the Power of Pseudo Label in Incremental Object Detection
  20. ICLR 2025Self-Normalized Resets for Plasticity in Continual Learning
  21. ICLR 2025Spurious Forgetting in Continual Learning of Language Models
  22. ICLR 2025STAR: Stability-Inducing Weight Perturbation for Continual Learning
  23. ICLR 2025Theory on Mixture-of-Experts in Continual Learning
  24. ICLR 2025Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning
  25. ICML 2025A Selective Learning Method for Temporal Graph Continual Learning
  26. ICML 2025Adapting to Evolving Adversaries with Regularized Continual Robust Training
  27. ICML 2025Adjusting Model Size in Continual Gaussian Processes: How Big is Big Enough?
  28. ICML 2025BECAME: Bayesian Continual Learning with Adaptive Model Merging
  29. ICML 2025Confounder-Free Continual Learning via Recursive Feature Normalization
  30. ICML 2025Continual Generalized Category Discovery: Learning and Forgetting from a Bayesian Perspective
  31. ICML 2025Continual Reinforcement Learning by Planning with Online World Models
  32. ICML 2025Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector
  33. ICML 2025Discovering a Zero (Zero-Vector Class of Machine Learning)
  34. ICML 2025FedSSI: Rehearsal-Free Continual Federated Learning with Synergistic Synaptic Intelligence
  35. ICML 2025LADA: Scalable Label-Specific CLIP Adapter for Continual Learning
  36. ICML 2025Large Continual Instruction Assistant
  37. ICML 2025Learning without Isolation: Pathway Protection for Continual Learning
  38. ICML 2025Measuring Representational Shifts in Continual Learning: A Linear Transformation Perspective
  39. ICML 2025Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn
  40. ICML 2025Model Uncertainty Quantification by Conformal Prediction in Continual Learning
  41. ICML 2025Online Curvature-Aware Replay: Leveraging $\mathbf{2^{nd}}$ Order Information for Online Continual Learning
  42. ICML 2025Optimal Task Order for Continual Learning of Multiple Tasks
  43. ICML 2025Overtrained Language Models Are Harder to Fine-Tune
  44. ICML 2025Position: Lifetime tuning is incompatible with continual reinforcement learning
  45. ICML 2025Predicting the Susceptibility of Examples to Catastrophic Forgetting
  46. ICML 2025Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective
  47. ICML 2025SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction Tuning
  48. ICML 2025The Importance of Being Lazy: Scaling Limits of Continual Learning
  49. ICML 2025Towards Understanding Catastrophic Forgetting in Two-layer Convolutional Neural Networks
  50. ICML 2025Understanding the Forgetting of (Replay-based) Continual Learning via Feature Learning: Angle Matters

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