mlsanityData to 7 Oct 2026

A Comprehensive Survey of Continual Learning: Theory, Method and Application

arXiv 2302.00487 ↗First posted 31 Jan 2023cs.LG cs.AI cs.CVcited by 860

Not on the map. Why?

Cited by 35 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

To cope with real-world dynamics, an intelligent system needs to incrementally acquire, update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as continual learning, provides a foundation for AI systems to develop themselves adaptively. In a general sense, continual learning is explicitly limited by catastrophic forgetting, where learning a new task usually results in a dramatic performance degradation of the old tasks. Beyond this, increasingly numerous advances have emerged in recent years that largely extend the understanding and application of continual learning. The growing and widespread interest in this direction demonstrates its realistic significance as well as complexity. In this work, we present a comprehensive survey of continual learning, seeking to bridge the basic settings, theoretical foundations, representative methods, and practical applications. Based on existing theoretical and empirical results, we summarize the general objectives of continual learning as ensuring a proper stability-plasticity trade-off and an adequate intra/inter-task generalizability in the context of resource efficiency. Then we provide a state-of-the-art and elaborated taxonomy, extensively analyzing how representative methods address continual learning, and how they are adapted to particular challenges in realistic applications. Through an in-depth discussion of promising directions, we believe that such a holistic perspective can greatly facilitate subsequent exploration in this field and beyond.

Key facts. Cited by 860 papers in the map (data through 7 Oct 2026). Builds on 378 of its 541 references that are in the map. First posted on arXiv 31 Jan 2023.

Builds on

378 of 541 references.

References · 378

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  8. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  9. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  10. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  11. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  12. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
38 more
  1. 2017Neural Discrete Representation Learningcited by 4,650
  2. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  3. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  4. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  6. 2015Fast R-CNNcited by 2,930
  7. 2016Learning without Forgettingcited by 2,465
  8. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  9. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  10. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  11. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  12. 2020Knowledge Distillation: A Surveycited by 1,578
  13. 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,404
  14. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,366
  15. 2016On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minimacited by 1,337
  16. 2016Progressive Neural Networkscited by 1,332
  17. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
  18. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
  19. 2019Objects as Pointscited by 1,172
  20. 2017Continual Learning with Deep Generative Replaycited by 1,152
  21. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,094
  22. 2018Experience Replay for Continual Learningcited by 1,074
  23. 2018Efficient Lifelong Learning with A-GEMcited by 1,044
  24. 2019Machine Unlearningcited by 1,020
  25. 2021Transformers in Vision: A Surveycited by 1,009
  26. 2021Learning to Prompt for Continual Learningcited by 938
  27. 2017A Closer Look at Memorization in Deep Networkscited by 936
  28. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 895
  29. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 882
  30. 2015Optimizing Neural Networks with Kronecker-factored Approximate Curvaturecited by 776
  31. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 734
  32. 2019Large Scale Incremental Learningcited by 727
  33. 2017Lifelong Learning with Dynamically Expandable Networkscited by 689
  34. 2018Overcoming catastrophic forgetting with hard attention to the taskcited by 672
  35. 2022DualPrompt: Complementary Prompting for Rehearsal-free Continual Learningcited by 635
  36. 2019Three scenarios for continual learningcited by 610
  37. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 599
  38. 2018End-to-End Incremental Learningcited by 596

50 most cited of 378 All 378 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 80; 2024: 232; 2025: 316; 2026: 232.

860 papers.

Sort:

By area:

  1. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  2. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  3. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 236
  4. 2024Continual Learning of Large Language Models: A Comprehensive Surveycited by 228
  5. 2024InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learningcited by 189
  6. 2023Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Needcited by 183
  7. 2023Mitigating the Alignment Tax of RLHFcited by 181
  8. 2023SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Modelcited by 178
  9. 2023RanPAC: Random Projections and Pre-trained Models for Continual Learningcited by 162
  10. 2025RL's Razor: Why Online Reinforcement Learning Forgets Lesscited by 162
  11. 2024A Comprehensive Study of Knowledge Editing for Large Language Modelscited by 157
  12. 2024Continual Learning with Pre-Trained Models: A Surveycited by 151
38 more
  1. 2023Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimalitycited by 121
  2. 2024Vision-Language Models for Medical Report Generation and Visual Question Answering: A Reviewcited by 121
  3. 2026SoK: Agentic Skills -- Beyond Tool Use in LLM Agentscited by 120
  4. 2024Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methodscited by 114
  5. 2023Foundational Models Defining a New Era in Vision: A Survey and Outlookcited by 109
  6. 2023Mixture of Cluster-conditional LoRA Experts for Vision-language Instruction Tuningcited by 106
  7. 2024VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?cited by 98
  8. 2024From Matching to Generation: A Survey on Generative Information Retrievalcited by 89
  9. 2023FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learningcited by 86
  10. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 78
  11. 2024Foundation Model for Advancing Healthcare: Challenges, Opportunities, and Future Directionscited by 77
  12. 2024Continual Learning and Catastrophic Forgettingcited by 73
  13. 2023A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learningcited by 66
  14. 2023LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discoverycited by 63
  15. 2025SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learningcited by 60
  16. 2023TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Modelscited by 59
  17. 2023Continual Learning: Applications and the Road Forwardcited by 59
  18. 2024Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learningcited by 53
  19. 2025End-to-End Test-Time Training for Long Contextcited by 53
  20. 2024Consistent Prompting for Rehearsal-Free Continual Learningcited by 52
  21. 2023CaT: Balanced Continual Graph Learning with Graph Condensationcited by 50
  22. 2024Theory on Mixture-of-Experts in Continual Learningcited by 50
  23. 2023UnIVAL: Unified Model for Image, Video, Audio and Language Taskscited by 44
  24. 2023Incorporating Neuro-Inspired Adaptability for Continual Learning in Artificial Intelligencecited by 43
  25. 2024Mixture of Experts Meets Prompt-Based Continual Learningcited by 43
  26. 2024Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancementcited by 43
  27. 2023Weighted Ensemble Models Are Strong Continual Learnerscited by 41
  28. 2024Recent Advances of Multimodal Continual Learning: A Comprehensive Surveycited by 39
  29. 2024Online DPO: Online Direct Preference Optimization with Fast-Slow Chasingcited by 38
  30. 2024R+X: Retrieval and Execution from Everyday Human Videoscited by 36
  31. 2023Continual Learning as Computationally Constrained Reinforcement Learningcited by 35
  32. 2024Make Continual Learning Stronger via C-Flatcited by 35
  33. 2026MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wildcited by 35
  34. 2024Alignment of Diffusion Models: Fundamentals, Challenges, and Futurecited by 34
  35. 2024LeanAgent: Lifelong Learning for Formal Theorem Provingcited by 34
  36. 2024Resurrecting Old Classes with New Data for Exemplar-Free Continual Learningcited by 33
  37. 2023A Unified Approach to Domain Incremental Learning with Memory: Theory and Algorithmcited by 32
  38. 2023Foundation Models for Weather and Climate Data Understanding: A Comprehensive Surveycited by 32

50 most cited of 860 All 860 (JSON)