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 1 / 8 页

  1. CVPR 2026A Faster Path to Continual Learning
  2. CVPR 2026AdaPrior Bayesian-Inspired Adaptive Prior Correction for Long-Tailed Continual Learning
  3. CVPR 2026Affordance-First Decomposition for Continual Learning in Video-Language Understanding
  4. CVPR 2026CGL Advancing Continual GUI Learning via Reinforcement Fine-Tuning
  5. CVPR 2026CHEEM Continual Learning by Reuse New Adapt and Skip -
  6. CVPR 2026Continual Distillation of Teachers from Different Domains
  7. CVPR 2026Continual Learning for fMRI-Based Brain Disorder Diagnosis via Functional Connectivity
  8. CVPR 2026Critical Patch-Aware Sparse Prompting with Decoupled Training for Continual Learning
  9. CVPR 2026Elastic Weight Consolidation Done Right for Continual Learning
  10. CVPR 2026Exemplar-Free Continual Learning for State Space Models
  11. CVPR 2026Is Parameter Isolation Better for Prompt-Based Continual Learning
  12. CVPR 2026Multimodal Continual Instruction Tuning with Dynamic Gradient Guidance
  13. CVPR 2026Octopus History-Free Gradient Orthogonalization for Continual Learning in Multimodal Large
  14. CVPR 2026Parameter-efficient Continual Learning for Enhancing Plasticity without Forgetting under Limited
  15. CVPR 2026phi-DPO Fairness Direct Preference Optimization Approach to Continual Learning in
  16. CVPR 2026Re-evaluating Continual VQA Toward Fair and Robust Evaluation for Multimodal
  17. CVPR 2026Resolving the Stability-Plasticity Dilemma in Reinforcement Learning via Complementary Continual
  18. CVPR 2026Robustness Under Data Scarcity Few-Shot Continual Adversarial Training for Evolving
  19. CVPR 2026Spectral Mixture-of-Experts for Continual Learning
  20. CVPR 2026Subspace Alignment for CLIP-based Continual Learning via Canonical Correlation Analysis
  21. CVPR 2026Towards Dynamic Modality Alignment in Multimodal Continual Learning
  22. CVPR 2026Towards Stable Federated Continual Test-Time Adaptation in Wild World
  23. ICLR 2026Activation Function Design Sustains Plasticity in Continual Learning
  24. ICLR 2026Asymptotic analysis of shallow and deep forgetting in replay with neural collapse
  25. ICLR 2026Avoid Catastrophic Forgetting with Rank-1 Fisher from Diffusion Models
  26. ICLR 2026Detect, Decide, Unlearn: A Transfer-Aware Framework for Continual Learning
  27. ICLR 2026FIRE: Frobenius-Isometry Reinitialization for Balancing the Stability–Plasticity Tradeoff
  28. ICLR 2026FlyPrompt: Brain-Inspired Random-Expanded Routing with Temporal-Ensemble Experts for General Continual Learning
  29. ICLR 2026Forget Forgetting: Continual Learning in a World of Abundant Memory
  30. ICLR 2026Healthcare Insurance Fraud Detection via Continual Fiedler Vector Graph Model
  31. ICLR 2026HippoTune: A Hippocampal Associative Loop–Inspired Fine-Tuning Method for Continual Learning
  32. ICLR 2026IDER: IDEMPOTENT EXPERIENCE REPLAY FOR RELIABLE CONTINUAL LEARNING
  33. ICLR 2026LCA: Local Classifier Alignment for Continual Learning
  34. ICLR 2026Memory-Statistics Tradeoff in Continual Learning with Structural Regularization
  35. ICLR 2026Merge before Forget: A Single LoRA Continual Learning via Continual Merging
  36. ICLR 2026Multi-Synaptic Cooperation: A Bio-Inspired Framework for Robust and Scalable Continual Learning
  37. ICLR 2026Null-Space Filtering for Data-free Continual Model Merging: Preserving Transparency, Promoting Fidelity
  38. ICLR 2026One-Prompt Strikes Back: Sparse Mixture of Experts for Prompt-based Continual Learning
  39. ICLR 2026PAC-Bayes bounds for cumulative loss in Continual Learning
  40. ICLR 2026PACE: Pretrained Audio Continual Learning
  41. ICLR 2026PCLR: Progressively Compressed LoRA for Multimodal Continual Instruction Tuning
  42. ICLR 2026Pi-CCA: Prompt-Invariant CCA Certificates for Replay-Free Continual Multimodal Learning
  43. ICLR 2026Plug-and-Play Compositionality for Boosting Continual Learning with Foundation Models
  44. ICLR 2026Rethinking Continual Learning with Progressive Neural Collapse
  45. ICLR 2026Reversible Primitive–Composition Alignment for Continual Vision–Language Learning
  46. ICLR 2026Revisiting Weight Regularization for Low-Rank Continual Learning
  47. ICLR 2026Robust Selective Activation with Randomized Temporal K-Winner-Take-All in Spiking Neural Networks for Continual Learning
  48. ICLR 2026Sculpting Subspaces: Constrained Full Fine-Tuning in LLMs for Continual Learning
  49. ICLR 2026Two-Way Is Better Than One: Bidirectional Alignment with Cycle Consistency for Exemplar-Free Class-Incremental Learning
  50. ICLR 2026Understanding the Dynamics of Forgetting and Generalization in Continual Learning via the Neural Tangent Kernel

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