Related work

The foundational work on continual learning, 1991 to 2026: methods, theory, benchmarks, surveys, and the neuroscience of memory. Updated weekly; some carry our notes.

5 papers of 4,574Sort Recent · Most cited
  1. 2025
    CEM: A Data-Efficient Method for Large Language Models to Continue Evolving From MistakesHaokun Zhao, Jinyi Han, Jie Shi … Fei YuCIKM · Fudan University · East China Normal University · +1
    PDF ↗
  2. 2025
    Hierarchical Visual Prompt Learning for Continual Video Instance SegmentationJiahua Dong, Hui Yin, Wenqi Liang … Fahad Shahbaz KhanICCV · Mohamed bin Zayed University of Artificial Intelligence · Hunan University · +3
    PDF ↗
  3. 2025
    Think Small, Act Big: Primitive Prompt Learning for Lifelong Robot ManipulationY. Lawrence Yao, Siao Liu, Haoming Song … Dong WangCVPR · ShangHai JiAi Genetics & IVF Institute · Shanghai Artificial Intelligence Laboratory · +2
    PDF ↗
  4. 2025
    PECTP: Parameter-Efficient Cross-Task Prompts for Incremental Vision TransformerQian Feng, Hanbin Zhao, Chao Zhang … Hui QianIEEE TCSVT · Zhejiang University of Science and Technology · Zhejiang University · +2
    PDF ↗
  5. 2025
    Instruct Where the Model Fails: Generative Data Augmentation via Guided Self-contrastive Fine-tuningWeijian Ma, Ruoxin Chen, Ke-Yue Zhang … Shouhong DingAAAI · Fudan University · Tencent (China)
    PDF ↗
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, and only papers with a PDF we can point you at, so every title opens the paper itself. 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.