持续学习论文趋势 2023–2026

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。

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 28 篇，第 1 / 1 页

1. ICLR 2026Activation Function Design Sustains Plasticity in Continual Learning
2. ICLR 2026Asymptotic analysis of shallow and deep forgetting in replay with neural collapse
3. ICLR 2026Avoid Catastrophic Forgetting with Rank-1 Fisher from Diffusion Models
4. ICLR 2026Detect, Decide, Unlearn: A Transfer-Aware Framework for Continual Learning
5. ICLR 2026FIRE: Frobenius-Isometry Reinitialization for Balancing the Stability–Plasticity Tradeoff
6. ICLR 2026FlyPrompt: Brain-Inspired Random-Expanded Routing with Temporal-Ensemble Experts for General Continual Learning
7. ICLR 2026Forget Forgetting: Continual Learning in a World of Abundant Memory
8. ICLR 2026Healthcare Insurance Fraud Detection via Continual Fiedler Vector Graph Model
9. ICLR 2026HippoTune: A Hippocampal Associative Loop–Inspired Fine-Tuning Method for Continual Learning
10. ICLR 2026IDER: IDEMPOTENT EXPERIENCE REPLAY FOR RELIABLE CONTINUAL LEARNING
11. ICLR 2026LCA: Local Classifier Alignment for Continual Learning
12. ICLR 2026Memory-Statistics Tradeoff in Continual Learning with Structural Regularization
13. ICLR 2026Merge before Forget: A Single LoRA Continual Learning via Continual Merging
14. ICLR 2026Multi-Synaptic Cooperation: A Bio-Inspired Framework for Robust and Scalable Continual Learning
15. ICLR 2026Null-Space Filtering for Data-free Continual Model Merging: Preserving Transparency, Promoting Fidelity
16. ICLR 2026One-Prompt Strikes Back: Sparse Mixture of Experts for Prompt-based Continual Learning
17. ICLR 2026PAC-Bayes bounds for cumulative loss in Continual Learning
18. ICLR 2026PACE: Pretrained Audio Continual Learning
19. ICLR 2026PCLR: Progressively Compressed LoRA for Multimodal Continual Instruction Tuning
20. ICLR 2026Pi-CCA: Prompt-Invariant CCA Certificates for Replay-Free Continual Multimodal Learning
21. ICLR 2026Plug-and-Play Compositionality for Boosting Continual Learning with Foundation Models
22. ICLR 2026Rethinking Continual Learning with Progressive Neural Collapse
23. ICLR 2026Reversible Primitive–Composition Alignment for Continual Vision–Language Learning
24. ICLR 2026Revisiting Weight Regularization for Low-Rank Continual Learning
25. ICLR 2026Robust Selective Activation with Randomized Temporal K-Winner-Take-All in Spiking Neural Networks for Continual Learning
26. ICLR 2026Sculpting Subspaces: Constrained Full Fine-Tuning in LLMs for Continual Learning
27. ICLR 2026Two-Way Is Better Than One: Bidirectional Alignment with Cycle Consistency for Exemplar-Free Class-Incremental Learning
28. ICLR 2026Understanding the Dynamics of Forgetting and Generalization in Continual Learning via the Neural Tangent Kernel

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。