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

131 papers, page 2 of 3

51. ICML 2026Adversarial Latent Embedding Repair for LLM Continual Learning
52. ICML 2026Beyond Buffer Limits: Energy-Based Data Reassembly for Continual Learning
53. ICML 2026BTSP-CAM: A Brain-Inspired Geometric Memory for Class-Incremental Learning
54. ICML 2026Capacity-Agnostic Parameter Isolation for Continual Graph Learning
55. ICML 2026CE$^4$L: Continual Ego, Exo, and Ego-Exo Learning
56. ICML 2026Continual Learning of Domain-Invariant Representations
57. ICML 2026Continual Learning through Control Minimization
58. ICML 2026Continual Model Routing in Evolving Model Hubs
59. ICML 2026Cross-task Calibration for Asynchronous Federated Continual Learning
60. ICML 2026Don't Forget Why You Started: Tackling Dual Forgetting in Vision-Language Continual Learning
61. ICML 2026Factor-Wise Homogeneity of Slot-Attention for Continual Object-Centric Learning
62. ICML 2026Forgetting Whenever You Want: A Decentralized Continual Learning Framework with On-Demand Unlearning
63. ICML 2026HTAC: Hierarchical Task-Aware Composition for Continual Offline Reinforcement Learning
64. ICML 2026HypCL: Adapting CLIP in Hyperbolic Space for Continual Learning
65. ICML 2026Hyperbolic Multimodal Continual Learning
66. ICML 2026JANUS-LORA: A Balanced Low-Rank Adaptation for Continual Learning
67. ICML 2026Little By Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts
68. ICML 2026Merge to Remember: Sharpness-Aware Isotropic Merging for Continual Learning
69. ICML 2026Mixing Expertise with Confidence: A Mixture of Experts Framework for Robust Multi-Modal Continual Learning
70. ICML 2026MoCL: Metabolic Optimization for Curvature-Aware Continual Learning
71. ICML 2026Multi-Head Attention as a Source of Catastrophic Forgetting in MoE Transformers
72. ICML 2026Neuro-evolutionary Continual Reinforcement Learning
73. ICML 2026On the Theory of Continual Learning with Gradient Descent for Neural Networks
74. ICML 2026Online Continual Learning with Dynamic Label Hierarchies
75. ICML 2026Plasticity Activation via Polar Operator: A Plug-in Method for Balancing Stability and Plasticity
76. ICML 2026Preserving Plasticity in Continual Learning via Dynamical Isometry
77. ICML 2026RC-FCL: Combating Asynchronous Concept Drift in Federated Continual Learning via Retrospective Calibration
78. ICML 2026Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training
79. ICML 2026Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting
80. ICML 2026SABER: Continual Learning with Representation Conflict Management
81. ICML 2026SAOT: Self-Supervised Continual Graph Learning with Structure-Aware Optimal Transport
82. ICML 2026SCNS: Continual Personalization of Diffusion Models via Submodular Concept Neuron Selection
83. ICML 2026Self-Distillation Enables Continual Learning
84. ICML 2026Shapley Neuron Values for Continual Learning: Which Neurons Matter Most?
85. ICML 2026Sharpness-Aware Pretraining Mitigates Catastrophic Forgetting
86. ICML 2026Skill Neologisms: Towards Skill-based Continual Learning
87. ICML 2026Spectral Collapse Drives Loss of Plasticity in Deep Continual Learning
88. ICML 2026The Forgetting-Retention Dilemma: Certified Unlearning Theory in Continual Learning
89. ICML 2026Turning Back Without Forgetting: Selective Backward Refinement for Parameter-Efficient Continual Learning
90. ICML 2026Understanding Generalization and Forgetting in In-Context Continual Learning
91. ICML 2026Unlocking the Potential of Continual Model Merging: An ODE Perspective
92. ICML 2026Updating Parametric Knowledge with Context Distillation Retains Post-Training Capabilities
93. NeurIPS 2026A Theoretical Bridge Between Long-Tailed Recognition and Continual Learning
94. NeurIPS 2026Anchoring Physiological Invariance, Expanding Domain Plasticity: Prior-Stabilized Dynamic Adaptation for Continual rPPG Measurement
95. NeurIPS 2026Bayes-pFCL:Bayesian Personalized Federated Continual Learning
96. NeurIPS 2026Beyond Exemplar Selection: Value-Aware Memory Allocation in Replay-Based Continual Learning
97. NeurIPS 2026Combating Catastrophic Forgetting in Continual Domain Adaptation via Knowledge Recasting
98. NeurIPS 2026Concentrated Gradients Amplify Forgetting: Dominant-direction Projection for Continual Multimodal Learning
99. NeurIPS 2026Continual Learning in Modern Hopfield Networks with an Application to Diffusion Models
100. NeurIPS 2026Data-Free Reservoir Features for Efficient Long-Horizon Cold-Start Continual Learning

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.