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.

8 papers of 6,493Sort Recent · Most cited
  1. 2025
    Expanding the Category of Classifiers with LLM SupervisionDerui Lyu, Xiangyu Wang, Taiyu Ban … Huanhuan ChenIJCAI · University of Science and Technology of China
    PDF ↗
  2. 2025
    Controllable Relation Disentanglement for Few-Shot Class-Incremental LearningYuan Zhou, Richang Hong, Yanrong Guo … Hanwang ZhangIEEE TCSVT · Nanyang Technological University · Hefei University of Technology · +1
    PDF ↗
  3. 2025
    Re-examine all-in-one image restoration: A catastrophic forgetting perspectiveChen Wu, Pu Wang, Zhuoran ZhengPattern Recognition Letters · University of Science and Technology of China · Shandong University · +2
  4. 2025
    Leveraging Multiple Deep Experts for Online Class-incremental LearningZhe Tao, Lu Yu, Hantao Yao, Changsheng XuIEEE International Conference on Multimedia and Expo (ICME) · Tianjin University of Technology · University of Science and Technology of China · +2
  5. 2025
    Language Guided Concept Bottleneck Models for Interpretable Continual LearningLu Yu, Haoyu Han, Zhe Tao … Chris XuCVPR · Tianjin University of Technology · University of Science and Technology of China · +2
    PDF ↗
  6. 2025
    GCD: Advancing Vision-Language Models for Incremental Object Detection via Global Alignment and Correspondence DistillationXu Wang, Zilei Wang, Zihan LinAAAI · University of Science and Technology of China
    PDF ↗
  7. 2025
    DCFT: Dependency-aware continual learning fine-tuning for sparse LLMsYanzhe Wang, Yizhen Wang, Baoqun YinNeurocomputing · University of Science and Technology of China
  8. 2025
    Multi-Prototype Grouping for Continual Learning in Visual Question AnsweringLicheng Zhang, Zhendong Mao, Yixing Peng … Yongdong ZhangICASSP · University of Science and Technology of China
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.