Continual Learning papers, 2023–2026

Key findings

• Continual Learning went from 77 papers in 2023 to 131 in 2026, roughly 1.7x in three years.
• NeurIPS publishes the most Continual Learning work: 121 papers from 2023 to 2026, 32% of the four-venue total.
• The fastest-growing overlap is with Low-Rank Adaptation: papers tagged with both rose from 1 in 2023 to 16 in 2026.
• Among the 5 topics under Meta-Learning and Transfer, it ranks #5 by 2026 paper count; the fastest grower in the group, Foundation Model Adaptation, is up 3.8x versus 1.7x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Continual Learning papers

101 papers, page 2 of 3

51. ICML 2025Discovering a Zero (Zero-Vector Class of Machine Learning)
52. ICML 2025FedSSI: Rehearsal-Free Continual Federated Learning with Synergistic Synaptic Intelligence
53. ICML 2025LADA: Scalable Label-Specific CLIP Adapter for Continual Learning
54. ICML 2025Large Continual Instruction Assistant
55. ICML 2025Learning without Isolation: Pathway Protection for Continual Learning
56. ICML 2025Measuring Representational Shifts in Continual Learning: A Linear Transformation Perspective
57. ICML 2025Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn
58. ICML 2025Model Uncertainty Quantification by Conformal Prediction in Continual Learning
59. ICML 2025Online Curvature-Aware Replay: Leveraging $\mathbf{2^{nd}}$ Order Information for Online Continual Learning
60. ICML 2025Optimal Task Order for Continual Learning of Multiple Tasks
61. ICML 2025Overtrained Language Models Are Harder to Fine-Tune
62. ICML 2025Position: Lifetime tuning is incompatible with continual reinforcement learning
63. ICML 2025Predicting the Susceptibility of Examples to Catastrophic Forgetting
64. ICML 2025Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective
65. ICML 2025SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction Tuning
66. ICML 2025The Importance of Being Lazy: Scaling Limits of Continual Learning
67. ICML 2025Towards Understanding Catastrophic Forgetting in Two-layer Convolutional Neural Networks
68. ICML 2025Understanding the Forgetting of (Replay-based) Continual Learning via Feature Learning: Angle Matters
69. ICML 2025Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective
70. ICML 2025Where is the Truth? The Risk of Getting Confounded in a Continual World
71. ICML 2025ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think
72. ICML 2024An Effective Dynamic Gradient Calibration Method for Continual Learning
73. ICML 2024COPAL: Continual Pruning in Large Language Generative Models
74. ICML 2024Disentangled Continual Graph Neural Architecture Search with Invariant Modular Supernet
75. ICML 2024Forget Sharpness: Perturbed Forgetting of Model Biases Within SAM Dynamics
76. ICML 2024Layerwise Proximal Replay: A Proximal Point Method for Online Continual Learning
77. ICML 2024Mitigating Catastrophic Forgetting in Online Continual Learning by Modeling Previous Task Interrelations via Pareto Optimization
78. ICML 2024On the Diminishing Returns of Width for Continual Learning
79. ICML 2024One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning
80. ICML 2024Provable Contrastive Continual Learning
81. ICML 2024Rapid Learning without Catastrophic Forgetting in the Morris Water Maze
82. ICML 2024Regularizing with Pseudo-Negatives for Continual Self-Supervised Learning
83. ICML 2024Self-Composing Policies for Scalable Continual Reinforcement Learning
84. ICML 2024Task-aware Orthogonal Sparse Network for Exploring Shared Knowledge in Continual Learning
85. ICML 2024Understanding Forgetting in Continual Learning with Linear Regression
86. ICML 2023Adaptive Compositional Continual Meta-Learning
87. ICML 2023BiRT: Bio-inspired Replay in Vision Transformers for Continual Learning
88. ICML 2023Constant Matters: Fine-grained Error Bound on Differentially Private Continual Observation
89. ICML 2023Continual Learners are Incremental Model Generalizers
90. ICML 2023Continual Learning in Linear Classification on Separable Data
91. ICML 2023Continual Vision-Language Representation Learning with Off-Diagonal Information
92. ICML 2023DDGR: Continual Learning with Deep Diffusion-based Generative Replay
93. ICML 2023Discrete Key-Value Bottleneck
94. ICML 2023Do You Remember? Overcoming Catastrophic Forgetting for Fake Audio Detection
95. ICML 2023Does Continual Learning Equally Forget All Parameters?
96. ICML 2023DualHSIC: HSIC-Bottleneck and Alignment for Continual Learning
97. ICML 2023Parameter-Level Soft-Masking for Continual Learning
98. ICML 2023Poisoning Generative Replay in Continual Learning to Promote Forgetting
99. ICML 2023Prototype-Sample Relation Distillation: Towards Replay-Free Continual Learning
100. ICML 2023The Ideal Continual Learner: An Agent That Never Forgets

FAQ

How many Continual Learning papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

381 in total: 77 in 2023, 69 in 2024, 104 in 2025, 131 in 2026.

How many Continual Learning papers are at NeurIPS 2026?

NeurIPS 2026 has 39 Continual Learning papers, versus 32 the year before.

How many Continual Learning papers are at ICLR 2026?

ICLR 2026 has 28 Continual Learning papers, versus 23 the year before.

How many Continual Learning papers are at ICML 2026?

ICML 2026 has 42 Continual Learning papers, versus 29 the year before.

How many Continual Learning papers are at CVPR 2026?

CVPR 2026 has 22 Continual Learning papers, versus 20 the year before.

Which conference publishes the most Continual Learning papers?

NeurIPS, with 121 papers from 2023 to 2026.