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
- 持续学习论文从 2023 年的 77 篇增长到 2026 年的 131 篇，三年间扩大到约 1.7 倍。
- NeurIPS 是发持续学习论文最多的会议，2023–2026 年共 121 篇，占四个会议总量的 32%。
- 交叉方向里涨得最快的是低秩适配：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 16 篇。
- 在「元学习与迁移」的 5 个主题里，它的 2026 年论文数排第 5；同组增长最快的基础模型适配是 3.8 倍，持续学习是 1.7 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 27 | 13 | 16 | 21 | 77 |
| 2024 | 23 | 14 | 14 | 18 | 69 |
| 2025 | 32 | 23 | 29 | 20 | 104 |
| 2026 | 39 | 28 | 42 | 22 | 131 |
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
- NeurIPS 2026Bayes-pFCL:Bayesian Personalized Federated Continual Learning
- ICML 2026Beyond Buffer Limits: Energy-Based Data Reassembly for Continual Learning
- ICLR 2026FlyPrompt: Brain-Inspired Random-Expanded Routing with Temporal-Ensemble Experts for General Continual Learning
- CVPR 2026A Faster Path to Continual Learning
- NeurIPS 2025AnaCP: Toward Upper-Bound Continual Learning via Analytic Contrastive Projection
- ICML 2025BECAME: Bayesian Continual Learning with Adaptive Model Merging
- ICLR 2025Active Learning for Continual Learning: Keeping the Past Alive in the Present
- CVPR 2025AdaptCMVC: Robust Adaption to Incremental Views in Continual Multi-view Clustering
- NeurIPS 2024CoIN: A Benchmark of Continual Instruction Tuning for Multimodel Large Language Models
- ICML 2024An Effective Dynamic Gradient Calibration Method for Continual Learning
- ICLR 2024A Probabilistic Framework for Modular Continual Learning
- CVPR 2024Defense without Forgetting: Continual Adversarial Defense with Anisotropic & Isotropic Pseudo Replay
- NeurIPS 2023Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
- ICML 2023Constant Matters: Fine-grained Error Bound on Differentially Private Continual Observation
- ICLR 2023Artificial Neuronal Ensembles with Learned Context Dependent Gating
- CVPR 2023Achieving a Better Stability-Plasticity Trade-Off via Auxiliary Networks in Continual Learning
- NeurIPS 2026Beyond Exemplar Selection: Value-Aware Memory Allocation in Replay-Based Continual Learning
- ICML 2026BTSP-CAM: A Brain-Inspired Geometric Memory for Class-Incremental Learning
- ICLR 2026IDER: IDEMPOTENT EXPERIENCE REPLAY FOR RELIABLE CONTINUAL LEARNING
- CVPR 2026AdaPrior Bayesian-Inspired Adaptive Prior Correction for Long-Tailed Continual Learning
全部持续学习论文
共 29 篇，第 1 / 1 页
- ICML 2025A Selective Learning Method for Temporal Graph Continual Learning
- ICML 2025Adapting to Evolving Adversaries with Regularized Continual Robust Training
- ICML 2025Adjusting Model Size in Continual Gaussian Processes: How Big is Big Enough?
- ICML 2025BECAME: Bayesian Continual Learning with Adaptive Model Merging
- ICML 2025Confounder-Free Continual Learning via Recursive Feature Normalization
- ICML 2025Continual Generalized Category Discovery: Learning and Forgetting from a Bayesian Perspective
- ICML 2025Continual Reinforcement Learning by Planning with Online World Models
- ICML 2025Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector
- ICML 2025Discovering a Zero (Zero-Vector Class of Machine Learning)
- ICML 2025FedSSI: Rehearsal-Free Continual Federated Learning with Synergistic Synaptic Intelligence
- ICML 2025LADA: Scalable Label-Specific CLIP Adapter for Continual Learning
- ICML 2025Large Continual Instruction Assistant
- ICML 2025Learning without Isolation: Pathway Protection for Continual Learning
- ICML 2025Measuring Representational Shifts in Continual Learning: A Linear Transformation Perspective
- ICML 2025Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn
- ICML 2025Model Uncertainty Quantification by Conformal Prediction in Continual Learning
- ICML 2025Online Curvature-Aware Replay: Leveraging $\mathbf{2^{nd}}$ Order Information for Online Continual Learning
- ICML 2025Optimal Task Order for Continual Learning of Multiple Tasks
- ICML 2025Overtrained Language Models Are Harder to Fine-Tune
- ICML 2025Position: Lifetime tuning is incompatible with continual reinforcement learning
- ICML 2025Predicting the Susceptibility of Examples to Catastrophic Forgetting
- ICML 2025Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective
- ICML 2025SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction Tuning
- ICML 2025The Importance of Being Lazy: Scaling Limits of Continual Learning
- ICML 2025Towards Understanding Catastrophic Forgetting in Two-layer Convolutional Neural Networks
- ICML 2025Understanding the Forgetting of (Replay-based) Continual Learning via Feature Learning: Angle Matters
- ICML 2025Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective
- ICML 2025Where is the Truth? The Risk of Getting Confounded in a Continual World
- ICML 2025ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think
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"}
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。