unify

Related work

The foundational work on continual learning, 1959 to 2026: methods, theory, benchmarks, surveys, and the neuroscience of memory. Updated weekly; some carry our notes.

7 papers of 11,817Sort Recent · Most cited
Fangzhou Xiong Clear all
  1. 2025
    Rethinking Long Context Generation from the Continual Learning PerspectiveZeyuan Yang, Fangzhou Xiong, Peng Li, Yang LiuCOLING
  2. 2021
    Zero-shot policy generation in lifelong reinforcement learningYiming Qian, Fangzhou Xiong, Zhiyong LiuNeurocomputing · Chinese Academy of Sciences · Shandong Institute of Automation · +2
  3. 2020
    State Primitive Learning to Overcome Catastrophic Forgetting in RoboticsFangzhou Xiong, Zhiyong Liu, Kaizhu Huang … Hong QiaoCognitive Computation · Shandong Institute of Automation · University of Chinese Academy of Sciences · +2
  4. 2020
    Encoding primitives generation policy learning for robotic arm to overcome catastrophic forgetting in sequential multi-tasks learningFangzhou Xiong, Zhiyong Liu, Kaizhu Huang … Amir HussainNeural Networks · Shandong Institute of Automation · Institute of Automation · +7
  5. 2019
    Primitives Generation Policy Learning without Catastrophic Forgetting for Robotic ManipulationFangzhou Xiong, Zhiyong Liu, Kaizhu Huang … Amir HussainICDM · Shandong Institute of Automation · University of Chinese Academy of Sciences · +4
  6. 2019
    Guided Policy Search for Sequential Multitask LearningFangzhou Xiong, Biao Sun, Xu Yang … Zhiyong LiuIEEE Transactions · University of Chinese Academy of Sciences · University of Science and Technology Beijing · +4
  7. 2018
    Overcoming Catastrophic Forgetting with Self-adaptive IdentifiersFangzhou Xiong, Zhiyong Liu, Xu YangSpringer LNCS · Shandong Institute of Automation · University of Chinese Academy of Sciences · +2
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 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.