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 381 篇，第 3 / 8 页

101. NeurIPS 2026Distance-Dependent Connectivity Shapes Continual Learning by Synaptic-Resource-Delimited Separation of Neural Dynamics
102. NeurIPS 2026Dynamic Cross-Modal Prompt Generation for Multimodal Continual Instruction Tuning
103. NeurIPS 2026FedSOUL: Federated Continual Unlearning via Spectral Orthogonality
104. NeurIPS 2026FedVaccine: Knowledge Recall after Spatial-Temporal Catastrophic Forgetting in Federated Continual Learning via Gradient-Based Vaccine
105. NeurIPS 2026FOGO: Forgetting-aware Orthogonalization Optimizer
106. NeurIPS 2026Forgetting Has Neighbors: Localized Collateral Forgetting in Machine Unlearning
107. NeurIPS 2026Forgetting to Improve: Principled Data Removal in Active Learning
108. NeurIPS 2026From Anti-Forgetting to Fast Adaptation: Continual Reinforcement Learning with World Models
109. NeurIPS 2026From Generic to Dedicated: A Novel Optimizer for Online Continual Learning
110. NeurIPS 2026HERO: A Heterogeneity-Aware Benchmark Library for Federated Continual Learning
111. NeurIPS 2026Heterogeneity-aware Distillation for Federated Continual Learning
112. NeurIPS 2026Hidden Forgetting in Continual Multimodal Learning: When Accuracy Survives but Grounding Fails
113. NeurIPS 2026Improving Continual Video Instance Segmentation via Spatial-Temporal Balanced Mixture-of-Experts Adapters
114. NeurIPS 2026InTAct: Interval-based Task Activation Consolidation for Continual Learning
115. NeurIPS 2026Lost or Hidden? A Concept-Level Forgetting in Supervised Continual Learning
116. NeurIPS 2026Mitigating Asymmetric Boundary Encroachment in Continual Learning of Vision-Language Models
117. NeurIPS 2026Modulating Merging Strengths via Joint Loss Estimation for LoRA-based Continual Learning
118. NeurIPS 2026MoRe: Modular Representations for Principled Continual Representation Learning on Sequential Data
119. NeurIPS 2026NADS: Navigator-Guided Data Selection for Mitigating Catastrophic Forgetting in Fine-Tuning
120. NeurIPS 2026Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning
121. NeurIPS 2026PM-LoRA: Scalable Continual Learning via Progressive Merging of Low Rank Adapters
122. NeurIPS 2026Spectral Rank Calibration for Continual LoRA Merging in Multimodal Large Language Models
123. NeurIPS 2026STABLE: A Continual Learning Optimizer with Adaptive Drift Control
124. NeurIPS 2026Subspace-Guided Continual Learning: Hessian Based Stable–Plastic Decomposition for Exemplar-Free Class-Incremental Learning
125. NeurIPS 2026Towards Better Generalization in Lifelong Person Re-Identification with Flatness-Aware Learning
126. NeurIPS 2026Trust Region Continual Learning as an Implicit Meta-Learner
127. NeurIPS 2026Two Drifts, One Principle: Conflict-Aware Spectral Consolidation for Multimodal Continual Learning
128. NeurIPS 2026UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning
129. NeurIPS 2026Unlearning Diffusion Policies via Relative Fisher Forgetting
130. NeurIPS 2026Unlocking Compositional Generalization in Continual Few-Shot Learning
131. NeurIPS 2026When Catastrophic Inheritance Meets Forgetting in Continual Adaptation of Foundation Models
132. CVPR 2025AdaptCMVC: Robust Adaption to Incremental Views in Continual Multi-view Clustering
133. CVPR 2025Advancing Multiple Instance Learning with Continual Learning for Whole Slide Imaging
134. CVPR 2025Beyond Background Shift: Rethinking Instance Replay in Continual Semantic Segmentation
135. CVPR 2025BiLoRA: Almost-Orthogonal Parameter Spaces for Continual Learning
136. CVPR 2025CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering
137. CVPR 2025ConceptGuard: Continual Personalized Text-to-Image Generation with Forgetting and Confusion Mitigation
138. CVPR 2025Continual SFT Matches Multimodal RLHF with Negative Supervision
139. CVPR 2025Do Your Best and Get Enough Rest for Continual Learning
140. CVPR 2025FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding
141. CVPR 2025Handling Spatial-Temporal Data Heterogeneity for Federated Continual Learning via Tail Anchor
142. CVPR 2025KAC: Kolmogorov-Arnold Classifier for Continual Learning
143. CVPR 2025Language Guided Concept Bottleneck Models for Interpretable Continual Learning
144. CVPR 2025LoRA Subtraction for Drift-Resistant Space in Exemplar-Free Continual Learning
145. CVPR 2025One-for-More: Continual Diffusion Model for Anomaly Detection
146. CVPR 2025Online Task-Free Continual Learning via Dynamic Expansionable Memory Distribution
147. CVPR 2025ProtoDepth: Unsupervised Continual Depth Completion with Prototypes
148. CVPR 2025Rethinking Query-based Transformer for Continual Image Segmentation
149. CVPR 2025Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learning
150. CVPR 2025Synthetic Data is an Elegant GIFT for Continual Vision-Language Models

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。