unify

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.

6 papers of 6,984Sort Recent · Most cited
IEEE Transactions South China University of Technology Clear all
  1. 2026
    Federated Class Incremental Learning Method With High Accuracy and Extremely Low Communication Cost Based on Broad Learning SystemJie Du, Wenbing Chen, Peng Liu … C L Philip ChenIEEE Transactions · Shenzhen University · University of Electronic Science and Technology of China · +2
  2. 2026
    Decision Boundary Drift: A Security, Privacy, and Trust Risk of Continual Learning for Agentic AI in Edge NetworksKaixiang Yang, Yue Xu, Zhihao Li … C.L. Philip ChenIEEE Transactions · Lanzhou University of Technology · South China University of Technology · +2
  3. 2025
    Hybrid Ensemble Framework for Imbalanced Data Streams With Concept DriftMianfen Lin, Zhiwen Yu, Kaixiang Yang, C. L. Philip ChenIEEE Transactions · South China University of Technology
  4. 2025
    Fully Few-Shot Class-Incremental Audio Classification With Adaptive Improvement of Stability and PlasticityYongjie Si, Yanxiong Li, Jiaxin Tan … Mladen RussoIEEE Transactions · South China University of Technology · University of Split
  5. 2024
    Federated Class-Incremental Learning With Dynamic Feature Extractor FusionYanyan Lu, Lei Yang, Hao-Rui Chen … Saiqin LongIEEE Transactions · South China University of Technology · Jinan University
  6. 2019
    Hierarchical Lifelong Learning by Sharing Representations and Integrating HypothesisTong Zhang, Guoxi Su, Chunmei Qing … Xiaofen XingIEEE Transactions · South China University of Technology
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.