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 1 / 3 页

  1. NeurIPS 2026A Theoretical Bridge Between Long-Tailed Recognition and Continual Learning
  2. NeurIPS 2026Anchoring Physiological Invariance, Expanding Domain Plasticity: Prior-Stabilized Dynamic Adaptation for Continual rPPG Measurement
  3. NeurIPS 2026Bayes-pFCL:Bayesian Personalized Federated Continual Learning
  4. NeurIPS 2026Beyond Exemplar Selection: Value-Aware Memory Allocation in Replay-Based Continual Learning
  5. NeurIPS 2026Combating Catastrophic Forgetting in Continual Domain Adaptation via Knowledge Recasting
  6. NeurIPS 2026Concentrated Gradients Amplify Forgetting: Dominant-direction Projection for Continual Multimodal Learning
  7. NeurIPS 2026Continual Learning in Modern Hopfield Networks with an Application to Diffusion Models
  8. NeurIPS 2026Data-Free Reservoir Features for Efficient Long-Horizon Cold-Start Continual Learning
  9. NeurIPS 2026Distance-Dependent Connectivity Shapes Continual Learning by Synaptic-Resource-Delimited Separation of Neural Dynamics
  10. NeurIPS 2026Dynamic Cross-Modal Prompt Generation for Multimodal Continual Instruction Tuning
  11. NeurIPS 2026FedSOUL: Federated Continual Unlearning via Spectral Orthogonality
  12. NeurIPS 2026FedVaccine: Knowledge Recall after Spatial-Temporal Catastrophic Forgetting in Federated Continual Learning via Gradient-Based Vaccine
  13. NeurIPS 2026FOGO: Forgetting-aware Orthogonalization Optimizer
  14. NeurIPS 2026Forgetting Has Neighbors: Localized Collateral Forgetting in Machine Unlearning
  15. NeurIPS 2026Forgetting to Improve: Principled Data Removal in Active Learning
  16. NeurIPS 2026From Anti-Forgetting to Fast Adaptation: Continual Reinforcement Learning with World Models
  17. NeurIPS 2026From Generic to Dedicated: A Novel Optimizer for Online Continual Learning
  18. NeurIPS 2026HERO: A Heterogeneity-Aware Benchmark Library for Federated Continual Learning
  19. NeurIPS 2026Heterogeneity-aware Distillation for Federated Continual Learning
  20. NeurIPS 2026Hidden Forgetting in Continual Multimodal Learning: When Accuracy Survives but Grounding Fails
  21. NeurIPS 2026Improving Continual Video Instance Segmentation via Spatial-Temporal Balanced Mixture-of-Experts Adapters
  22. NeurIPS 2026InTAct: Interval-based Task Activation Consolidation for Continual Learning
  23. NeurIPS 2026Lost or Hidden? A Concept-Level Forgetting in Supervised Continual Learning
  24. NeurIPS 2026Mitigating Asymmetric Boundary Encroachment in Continual Learning of Vision-Language Models
  25. NeurIPS 2026Modulating Merging Strengths via Joint Loss Estimation for LoRA-based Continual Learning
  26. NeurIPS 2026MoRe: Modular Representations for Principled Continual Representation Learning on Sequential Data
  27. NeurIPS 2026NADS: Navigator-Guided Data Selection for Mitigating Catastrophic Forgetting in Fine-Tuning
  28. NeurIPS 2026Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning
  29. NeurIPS 2026PM-LoRA: Scalable Continual Learning via Progressive Merging of Low Rank Adapters
  30. NeurIPS 2026Spectral Rank Calibration for Continual LoRA Merging in Multimodal Large Language Models
  31. NeurIPS 2026STABLE: A Continual Learning Optimizer with Adaptive Drift Control
  32. NeurIPS 2026Subspace-Guided Continual Learning: Hessian Based Stable–Plastic Decomposition for Exemplar-Free Class-Incremental Learning
  33. NeurIPS 2026Towards Better Generalization in Lifelong Person Re-Identification with Flatness-Aware Learning
  34. NeurIPS 2026Trust Region Continual Learning as an Implicit Meta-Learner
  35. NeurIPS 2026Two Drifts, One Principle: Conflict-Aware Spectral Consolidation for Multimodal Continual Learning
  36. NeurIPS 2026UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning
  37. NeurIPS 2026Unlearning Diffusion Policies via Relative Fisher Forgetting
  38. NeurIPS 2026Unlocking Compositional Generalization in Continual Few-Shot Learning
  39. NeurIPS 2026When Catastrophic Inheritance Meets Forgetting in Continual Adaptation of Foundation Models
  40. NeurIPS 2025AnaCP: Toward Upper-Bound Continual Learning via Analytic Contrastive Projection
  41. NeurIPS 2025Are Greedy Task Orderings Better Than Random in Continual Linear Regression?
  42. NeurIPS 2025Auto-Compressing Networks
  43. NeurIPS 2025C-NAV: Towards Self-Evolving Continual Object Navigation in Open World
  44. NeurIPS 2025Compact Memory for Continual Logistic Regression
  45. NeurIPS 2025Continual Knowledge Adaptation for Reinforcement Learning
  46. NeurIPS 2025Continual Multimodal Contrastive Learning
  47. NeurIPS 2025Continuous Subspace Optimization for Continual Learning
  48. NeurIPS 2025Contrastive Consolidation of Top-Down Modulations Achieves Sparsely Supervised Continual Learning
  49. NeurIPS 2025Decentralized Dynamic Cooperation of Personalized Models for Federated Continual Learning
  50. NeurIPS 2025Demystifying Language Model Forgetting with Low-rank Example Associations

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