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 121 篇，第 2 / 3 页

  1. NeurIPS 2025Dual-Space Semantic Synergy Distillation for Continual Learning of Unlabeled Streams
  2. NeurIPS 2025Dynamic Siamese Expansion Framework for Improving Robustness in Online Continual Learning
  3. NeurIPS 2025Federated Continual Learning via Orchestrating Multi-Scale Expertise
  4. NeurIPS 2025Gated Integration of Low-Rank Adaptation for Continual Learning of Large Language Models
  5. NeurIPS 2025Gradient-Guided Epsilon Constraint Method for Online Continual Learning
  6. NeurIPS 2025Hippocampal-like Sequential Editing for Continual Knowledge Updates in Large Language Models
  7. NeurIPS 2025Hybrid Re-matching for Continual Learning with Parameter-Efficient Tuning
  8. NeurIPS 2025Memory-Integrated Reconfigurable Adapters: A Unified Framework for Settings with Multiple Tasks
  9. NeurIPS 2025Merging on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging
  10. NeurIPS 2025MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging
  11. NeurIPS 2025Mitigating Intra- and Inter-modal Forgetting in Continual Learning of Unified Multimodal Models
  12. NeurIPS 2025Online Functional Tensor Decomposition via Continual Learning for Streaming Data Completion
  13. NeurIPS 2025Optimal Rates in Continual Linear Regression via Increasing Regularization
  14. NeurIPS 2025OVS Meets Continual Learning: Towards Sustainable Open-Vocabulary Segmentation
  15. NeurIPS 2025REP: Resource-Efficient Prompting for Rehearsal-Free Continual Learning
  16. NeurIPS 2025Self-Evolving Pseudo-Rehearsal for Catastrophic Forgetting with Task Similarity in LLMs
  17. NeurIPS 2025SPICED: A Synaptic Homeostasis-Inspired Framework for Unsupervised Continual EEG Decoding
  18. NeurIPS 2025Temporal-Difference Variational Continual Learning
  19. NeurIPS 2025The World Is Bigger: A Computationally-Embedded Perspective on the Big World Hypothesis
  20. NeurIPS 2025Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning
  21. NeurIPS 2025Turning the Tables: Enabling Backward Transfer via Causal-Aware LoRA in Continual Learning
  22. NeurIPS 2024A Topology-aware Graph Coarsening Framework for Continual Graph Learning
  23. NeurIPS 2024CoIN: A Benchmark of Continual Instruction Tuning for Multimodel Large Language Models
  24. NeurIPS 2024Continual Learning in the Frequency Domain
  25. NeurIPS 2024Continual Learning with Global Alignment
  26. NeurIPS 2024Continual learning with the neural tangent ensemble
  27. NeurIPS 2024Disentangling and mitigating the impact of task similarity for continual learning
  28. NeurIPS 2024Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learning
  29. NeurIPS 2024GACL: Exemplar-Free Generalized Analytic Continual Learning
  30. NeurIPS 2024Label Delay in Online Continual Learning
  31. NeurIPS 2024Learn more, but bother less: parameter efficient continual learning
  32. NeurIPS 2024Learning Successor Features the Simple Way
  33. NeurIPS 2024Leveraging Catastrophic Forgetting to Develop Safe Diffusion Models against Malicious Finetuning
  34. NeurIPS 2024Make Continual Learning Stronger via C-Flat
  35. NeurIPS 2024Mixture of Experts Meets Prompt-Based Continual Learning
  36. NeurIPS 2024Model Sensitivity Aware Continual Learning
  37. NeurIPS 2024Parseval Regularization for Continual Reinforcement Learning
  38. NeurIPS 2024Persistence Homology Distillation for Semi-supervised Continual Learning
  39. NeurIPS 2024Reawakening knowledge: Anticipatory recovery from catastrophic interference via structured training
  40. NeurIPS 2024Saliency-driven Experience Replay for Continual Learning
  41. NeurIPS 2024Task Confusion and Catastrophic Forgetting in Class-Incremental Learning: A Mathematical Framework for Discriminative and Generative Modelings
  42. NeurIPS 2024Train-Attention: Meta-Learning Where to Focus in Continual Knowledge Learning
  43. NeurIPS 2024Vector Quantization Prompting for Continual Learning
  44. NeurIPS 2024Visual Prompt Tuning in Null Space for Continual Learning
  45. NeurIPS 2023A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Tasks
  46. NeurIPS 2023A Definition of Continual Reinforcement Learning
  47. NeurIPS 2023Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
  48. NeurIPS 2023An Efficient Dataset Condensation Plugin and Its Application to Continual Learning
  49. NeurIPS 2023CL-NeRF: Continual Learning of Neural Radiance Fields for Evolving Scene Representation
  50. NeurIPS 2023CLeAR: Continual Learning on Algorithmic Reasoning for Human-like Intelligence

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