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 42 篇，第 1 / 1 页

1. ICML 2026Adversarial Latent Embedding Repair for LLM Continual Learning
2. ICML 2026Beyond Buffer Limits: Energy-Based Data Reassembly for Continual Learning
3. ICML 2026BTSP-CAM: A Brain-Inspired Geometric Memory for Class-Incremental Learning
4. ICML 2026Capacity-Agnostic Parameter Isolation for Continual Graph Learning
5. ICML 2026CE$^4$L: Continual Ego, Exo, and Ego-Exo Learning
6. ICML 2026Continual Learning of Domain-Invariant Representations
7. ICML 2026Continual Learning through Control Minimization
8. ICML 2026Continual Model Routing in Evolving Model Hubs
9. ICML 2026Cross-task Calibration for Asynchronous Federated Continual Learning
10. ICML 2026Don't Forget Why You Started: Tackling Dual Forgetting in Vision-Language Continual Learning
11. ICML 2026Factor-Wise Homogeneity of Slot-Attention for Continual Object-Centric Learning
12. ICML 2026Forgetting Whenever You Want: A Decentralized Continual Learning Framework with On-Demand Unlearning
13. ICML 2026HTAC: Hierarchical Task-Aware Composition for Continual Offline Reinforcement Learning
14. ICML 2026HypCL: Adapting CLIP in Hyperbolic Space for Continual Learning
15. ICML 2026Hyperbolic Multimodal Continual Learning
16. ICML 2026JANUS-LORA: A Balanced Low-Rank Adaptation for Continual Learning
17. ICML 2026Little By Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts
18. ICML 2026Merge to Remember: Sharpness-Aware Isotropic Merging for Continual Learning
19. ICML 2026Mixing Expertise with Confidence: A Mixture of Experts Framework for Robust Multi-Modal Continual Learning
20. ICML 2026MoCL: Metabolic Optimization for Curvature-Aware Continual Learning
21. ICML 2026Multi-Head Attention as a Source of Catastrophic Forgetting in MoE Transformers
22. ICML 2026Neuro-evolutionary Continual Reinforcement Learning
23. ICML 2026On the Theory of Continual Learning with Gradient Descent for Neural Networks
24. ICML 2026Online Continual Learning with Dynamic Label Hierarchies
25. ICML 2026Plasticity Activation via Polar Operator: A Plug-in Method for Balancing Stability and Plasticity
26. ICML 2026Preserving Plasticity in Continual Learning via Dynamical Isometry
27. ICML 2026RC-FCL: Combating Asynchronous Concept Drift in Federated Continual Learning via Retrospective Calibration
28. ICML 2026Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training
29. ICML 2026Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting
30. ICML 2026SABER: Continual Learning with Representation Conflict Management
31. ICML 2026SAOT: Self-Supervised Continual Graph Learning with Structure-Aware Optimal Transport
32. ICML 2026SCNS: Continual Personalization of Diffusion Models via Submodular Concept Neuron Selection
33. ICML 2026Self-Distillation Enables Continual Learning
34. ICML 2026Shapley Neuron Values for Continual Learning: Which Neurons Matter Most?
35. ICML 2026Sharpness-Aware Pretraining Mitigates Catastrophic Forgetting
36. ICML 2026Skill Neologisms: Towards Skill-based Continual Learning
37. ICML 2026Spectral Collapse Drives Loss of Plasticity in Deep Continual Learning
38. ICML 2026The Forgetting-Retention Dilemma: Certified Unlearning Theory in Continual Learning
39. ICML 2026Turning Back Without Forgetting: Selective Backward Refinement for Parameter-Efficient Continual Learning
40. ICML 2026Understanding Generalization and Forgetting in In-Context Continual Learning
41. ICML 2026Unlocking the Potential of Continual Model Merging: An ODE Perspective
42. ICML 2026Updating Parametric Knowledge with Context Distillation Retains Post-Training Capabilities

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。