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.

11 papers of 4,574Sort Recent · Most cited
  1. 2026
    Towards Experience Replay for Class-Incremental Learning in Fully-Binary NetworksYanis Basso-Bert, Anca Molnos, Romain Lemaire … Antoine DupretACM Transactions · Commissariat à l'Énergie Atomique et aux Énergies Alternatives · CEA Grenoble · +3
    PDF ↗
  2. 2025
    Bayesian continual learning and forgetting in neural networksDjohan Bonnet, Kellian Cottart, Tifenn Hirtzlin … Damien QuerliozNature Communications · Centre National de la Recherche Scientifique · Université Paris-Saclay · +4
    PDF ↗
  3. 2025
    Foundation vs. Specialized Models: Evaluating Catastrophic Forgetting in Continual Time Series ForecastingNouha Karaouli, Denis Coquenet, Élisa Fromont … Marina ReybozarXiv · Institut de Recherche en Informatique et Systèmes Aléatoires · Université de Rennes · +7
    PDF ↗
  4. 2024
    Novel-WD: Exploring acquisition of Novel World Knowledge in LLMs Using Prefix-TuningMaxime Méloux, Christophe CerisaraarXiv · Centre National de la Recherche Scientifique · Institut des langues et cultures d'Europe, Amérique, Afrique, Asie et Australie · +1
    PDF ↗
  5. 2023
    On the Effectiveness of LayerNorm Tuning for Continual Learning in Vision TransformersThomas De Min, Massimiliano Mancini, Karteek Alahari … Elisa RicciICCV · University of Trento · Institut polytechnique de Grenoble · +5
    PDF ↗
  6. 2022
    Federated Continual Learning through distillation in pervasive computingAnastasiia Usmanova, François Portet, Philippe Lalanda, Germán VegaInternational Conference on Smart Computing · Université Grenoble Alpes
    PDF ↗
  7. 2022
    Unseen Classes at a Later Time? No ProblemHari Chandana Kuchibhotla, Sumitra S Malagi, Shivam Chandhok, Vineeth N BalasubramanianCVPR · Indian Institute of Technology Hyderabad · Institut national de recherche en sciences et technologies du numérique · +1
    PDF ↗
  8. 2022
    Federated Learning and catastrophic forgetting in pervasive computing: demonstration in HAR domainAnastasiia Usmanova, François Portet, Philippe Lalanda, Germán VegaIEEE International Conference on Pervasive Computing and… · Université Grenoble Alpes · Laboratoire d'Informatique de Grenoble · +2
    PDF ↗
  9. 2018
    End-to-End Incremental LearningFrancisco M. Castro, Manuel J. Marín‐Jiménez, Nicolás Guil … Karteek AlahariECCV · Universidad de Málaga · University of Córdoba · +5
    PDF ↗
  10. 2017
    Incremental Learning of Object Detectors without Catastrophic ForgettingKonstantin Shmelkov, Cordelia Schmid, Karteek AlahariICCV · Institut polytechnique de Grenoble · Centre National de la Recherche Scientifique · +3
    PDF ↗
  11. 2013
    The stability-plasticity dilemma: investigating the continuum from catastrophic forgetting to age-limited learning effectsMartial Mermillod, Aurélia Bugaïska, Patrick BoninFrontiers · Centre National de la Recherche Scientifique · Institut Universitaire de France · +3
    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.