Related work

The foundational work on continual learning, 1989 to 2026: methods, theory, benchmarks, surveys, and the neuroscience of memory. Updated weekly; some carry our notes.

8 papers of 5,456Sort Recent · Most cited
  1. 2023
    Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category DiscoveryHyungmin Kim, Sungho Suh, Dae-Hwan Kim … Junmo KimICCV · Korea Advanced Institute of Science and Technology · Samsung (South Korea) · +3
    PDF ↗
  2. 2023
    Data Poisoning Attack Aiming the Vulnerability of Continual LearningGyojin Han, Jaehyun Choi, Hyeong Gwon Hong, Junmo KimICIP · Korea Advanced Institute of Science and Technology · International Graduate School of English
    PDF ↗
  3. 2022
    DLCFT: Deep Linear Continual Fine-Tuning for General Incremental LearningHyounguk Shon, Janghyeon Lee, Seung Hwan Kim, Junmo KimECCV
    PDF ↗
  4. 2020
    Continual Learning With Extended Kronecker-Factored Approximate CurvatureJanghyeon Lee, Hyeong Gwon Hong, Donggyu Joo, Junmo KimCVPR · Korea Advanced Institute of Science and Technology
    PDF ↗
  5. 2020
    Residual Continual LearningJanghyeon Lee, Donggyu Joo, Hyeong Gwon Hong, Junmo KimAAAI · Korea Advanced Institute of Science and Technology · Kootenay Association for Science & Technology
    PDF ↗
  6. 2019
    Collaborative Method for Incremental Learning on Classification and GenerationByungju Kim, Jae-Young Lee, Kyungsu Kim … Junmo KimICIP · Korea Advanced Institute of Science and Technology · Samsung (United States)
    PDF ↗
  7. 2018
    Incremental Learning in Deep Convolutional Neural Network VIA Adaptive RegularizationSihyeon Seong, Pyunghwan Ahn, Jiwhan Kim, Junmo KimIEEE International Conference on Consumer Electronics - A… · Korea Advanced Institute of Science and Technology
  8. 2016
    Less-forgetting Learning in Deep Neural NetworksHeechul Jung, Jeongwoo Ju, Minju Jung, Junmo KimarXiv
    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 written 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.