Related work

The foundational work on continual learning, 1988 to 2026: methods, theory, benchmarks, surveys, and the neuroscience of memory. Updated weekly; some carry our notes.

13 papers of 6,984Sort Recent · Most cited
  1. 2025
    Online Continual Learning via Dynamic Expandable Recursive ModelFei Ye, Adrian G. BorşACM International Conference on Multimedia · University of Electronic Science and Technology of China · Chengdu University of Information Technology · +1
    PDF ↗
  2. 2025
    Online Task-Free Continual Learning via Dynamic Expansionable Memory DistributionFei Ye, Adrian G. BorşCVPR · University of Electronic Science and Technology of China · University of York
    PDF ↗
  3. 2025
    Training a Dynamic Growing Mixture Model for Lifelong LearningFei Ye, Adrian G. BorşTNNLS · University of Electronic Science and Technology of China · University of York
    PDF ↗
  4. 2025
    Online task-free continual learning via Expansible Vision TransformerFei Ye, Adrian G. BorşPattern Recognition · University of Electronic Science and Technology of China · University of York
    PDF ↗
  5. 2025
    Online task-free continual learning via discrepancy mechanismFei Ye, Adrian G. BorşKnowledge-Based Systems · University of Electronic Science and Technology of China · University of York
    PDF ↗
  6. 2025
    Continual Unsupervised Generative ModelingFei Ye, Adrian G. BorşTPAMI · University of Electronic Science and Technology of China · University of York
    PDF ↗
  7. 2025
    Dynamic Expansion Diffusion Learning for Lifelong Generative ModellingFei Ye, Adrian G. Borş, Kun ZhangAAAI · University of Electronic Science and Technology of China · University of York · +1
    PDF ↗
  8. 2025
    Continual Unsupervised Generative Modelling via Online Optimal TransportFei Ye, Adrian G. Borş, Kun ZhangAAAI · University of Electronic Science and Technology of China · University of York · +2
    PDF ↗
  9. 2025
    Lifelong Scalable Generative System via Online Maximum Mean DiscrepancyFei Ye, Adrian G. BorşAAAI · University of Electronic Science and Technology of China · University of York
    PDF ↗
  10. 2025
    Evolving Ensemble Model based on Hilbert Schmidt Independence Criterion for task-free continual learningFei Ye, Adrian G. BorşNeurocomputing · University of Electronic Science and Technology of China · University of York
  11. 2025
    Dynamic Siamese Expansion Framework for Improving Robustness in Online Continual LearningFei Ye, Yulong Zhao, Qihe Liu … shijie zhouNeurIPS · University of Electronic Science and Technology of China · University of York
  12. 2025
    Learning Expandable and Adaptable Representations for Continual LearningRuilong Yu, Mingyan Liu, Fei Ye … shijie zhouNeurIPS · University of Electronic Science and Technology of China · Harbin Institute of Technology · +1
  13. 2025
    Learning Multi-Source and Robust Representations for Continual LearningFei Ye, yongcheng zhong, Qihe Liu … shijie zhouNeurIPS · University of Electronic Science and Technology of China · University of York
About this index

We keep this list because we read the field and wanted one place to see it. It covers work on continual learning itself, in the core areas of machine learning, and leaves out papers that apply it inside another field, such as medical imaging or fault diagnosis. It lists only papers we have a reason to trust: published at a venue like NeurIPS, ICML, ICLR, CVPR or TPAMI, or led by someone who has published there, or cited a few hundred times. Preprints that later get accepted, and authors who later publish at those venues, are picked up by the weekly run. It is seeded from the community lists kept by ContinualAI and by Xialei Liu, then filled out from OpenAlex, and every week a script looks for new papers on OpenAlex and arXiv. A model reads each candidate and decides whether it belongs; a person reviews the additions before they go live. Authors and affiliations come from OpenAlex, so a recent preprint can lack its institutions for a week or two.

Missing something, or filed under the wrong venue? Write to hello@unify.ai with the arXiv id or DOI.