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.

14 papers of 6,984Sort Recent · Most cited
  1. 2026PDF ↗
  2. 2025
    Teaching Prompts to Coordinate: Hierarchical Layer-Grouped Prompt Tuning for Continual LearningShengqin Jiang, T. Yung Kong, Yuankai Qi … Ming–Hsuan YangarXiv
    PDF ↗
  3. 2025PDF ↗
  4. 2025
    Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual LearningHuiyi Wang, Haodong Lu, Lina Yao, Dong GongCVPR · UNSW Sydney · Commonwealth Scientific and Industrial Research Organisation · +1
    PDF ↗
  5. 2025PDF ↗
  6. 2025PDF ↗
  7. 2025
  8. 2024PDF ↗
  9. 2025PDF ↗
  10. 2024PDF ↗
  11. 2024
    Exploring Soft Prompt Initialization Strategy for Few-Shot Continual Text ClassificationZhehao Zhang, Tong Yu, Handong Zhao … Shuai LiICASSP · Dartmouth College · Dartmouth Hospital · +6
  12. 2024
  13. 2023
    NPCL: Neural Processes for Uncertainty-Aware Continual LearningSaurav Jha, Dong Gong, He Zhao, Lina YaoNeurIPS
    PDF ↗
  14. 2023
    Uncertainty Estimation With Neural Processes for Meta-Continual LearningXuesong Wang, Lina Yao, Xianzhi Wang … Sen WangTNNLS · University of Technology Sydney · UNSW Sydney · +4
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.