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 78 篇，第 2 / 2 页

51. ICLR 2025Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning
52. ICLR 2024A Probabilistic Framework for Modular Continual Learning
53. ICLR 2024Accurate Forgetting for Heterogeneous Federated Continual Learning
54. ICLR 2024Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning
55. ICLR 2024Continual Learning in the Presence of Spurious Correlations: Analyses and a Simple Baseline
56. ICLR 2024Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation
57. ICLR 2024Continual Momentum Filtering on Parameter Space for Online Test-time Adaptation
58. ICLR 2024Efficient Continual Finite-Sum Minimization
59. ICLR 2024Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning
60. ICLR 2024Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks
61. ICLR 2024Meta Continual Learning Revisited: Implicitly Enhancing Online Hessian Approximation via Variance Reduction
62. ICLR 2024Prompt Gradient Projection for Continual Learning
63. ICLR 2024Scalable Language Model with Generalized Continual Learning
64. ICLR 2024The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting — An Analytical Model
65. ICLR 2024TiC-CLIP: Continual Training of CLIP Models
66. ICLR 2023Artificial Neuronal Ensembles with Learned Context Dependent Gating
67. ICLR 2023Building a Subspace of Policies for Scalable Continual Learning
68. ICLR 2023Continual evaluation for lifelong learning: Identifying the stability gap
69. ICLR 2023Continual Pre-training of Language Models
70. ICLR 2023Deja Vu: Continual Model Generalization for Unseen Domains
71. ICLR 2023Error Sensitivity Modulation based Experience Replay: Mitigating Abrupt Representation Drift in Continual Learning
72. ICLR 2023Is Forgetting Less a Good Inductive Bias for Forward Transfer?
73. ICLR 2023Learning without Prejudices: Continual Unbiased Learning via Benign and Malignant Forgetting
74. ICLR 2023New Insights for the Stability-Plasticity Dilemma in Online Continual Learning
75. ICLR 2023Online Boundary-Free Continual Learning by Scheduled Data Prior
76. ICLR 2023Optimizing Spca-based Continual Learning: A Theoretical Approach
77. ICLR 2023Progressive Prompts: Continual Learning for Language Models
78. ICLR 2023Sparse Distributed Memory is a Continual Learner

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。