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.

22 papers of 6,984Sort Recent · Most cited
  1. 2024
    Simple and Scalable Strategies to Continually Pre-train Large Language ModelsAdam Ibrahim, Benjamin Therien, Kshitij Gupta … Irina RishTMLR
    PDF ↗
  2. 2024
    Continual Learning of Deep Neural Networks in The Age of Big DataAlexander Gepperth, Timothée LesortESANN 2024 proceesdings · Fulda University of Applied Sciences · Altran (France)
    PDF ↗
  3. 2023
    Continual Learning Under Language ShiftEvangelia Gogoulou, Timothée Lesort, Magnus Boman, Joakim NivreInternational Conference on Text, Speech and Dialogue
    PDF ↗
  4. 2023
  5. 2022
    Beyond Supervised Continual Learning: a ReviewBenedikt Bagus, Alexander Gepperth, Timothée LesortarXiv
    PDF ↗
  6. 2023
    Challenging Common Assumptions about Catastrophic Forgetting and Knowledge AccumulationTimothée Lesort, Оleksiy Ostapenko, Diganta Misra … Irina RishCoLLAs
    PDF ↗
  7. 2022
    Continual Learning with Foundation Models: An Empirical Study of Latent ReplayОleksiy Ostapenko, Timothée Lesort, Pau Rodríguez … Laurent CharlinCoLLAs
    PDF ↗
  8. 2022PDF ↗
  9. 2022
    Tutorial - Continual Learning beyond classificationAlexander Gepperth, Timothée LesortESANN 2022 proceedings · Fulda University of Applied Sciences · Université de Montréal
    PDF ↗
  10. 2022
    Foundational Models for Continual Learning: An Empirical Study of Latent ReplayOleksiy Ostapenko, Timothée Lesort, P. Rodríguez … Laurent CharlinarXiv
  11. 2022
    Scaling the Number of Tasks in Continual LearningTimothée Lesort, Oleksiy Ostapenko, Diganta Misra … I. RisharXiv
  12. 2021
    Sequoia: A Software Framework to Unify Continual Learning ResearchFabrice Normandin, Florian Golemo, Oleksiy Ostapenko … M. CacciaarXiv
    PDF ↗
  13. 2021
    Continual Learning in Deep Networks: an Analysis of the Last LayerTimothée Lesort, Thomas George, Irina RisharXiv
    PDF ↗
  14. 2021PDF ↗
  15. 2021
    Continuum: Simple Management of Complex Continual Learning ScenariosArthur Douillard, Timothée LesortarXiv · Mila - Quebec Artificial Intelligence Institute
    PDF ↗
  16. 2020PDF ↗
  17. 2020
  18. 2019
    Continual Learning for RoboticsTimothée Lesort, Vincenzo Lomonaco, Andrei Stoian … Natalia Díaz-RodríguezInformation Fusion · Thales (Portugal) · Institut national de recherche en sciences et technologies du numérique · +3
    PDF ↗
  19. 2019
    Regularization Shortcomings for Continual LearningTimothée Lesort, Andrei Stoian, Filliat, DavidarXiv · École d'Ingénieurs en Chimie et Sciences du Numérique · Thales (Portugal)
    PDF ↗
  20. 2019
    Generative Models from the perspective of Continual LearningTimothée Lesort, Hugo Caselles-Dupré, Michael Garcia-Ortiz … David FilliatIEEE International Joint Conference on Neural Network · Institut national de recherche en sciences et technologies du numérique · École Nationale Supérieure de Techniques Avancées · +2
    PDF ↗
  21. 2019
    Continual Reinforcement Learning deployed in Real-life using Policy Distillation and Sim2Real TransferRené Traoré, Hugo Caselles-Dupré, Timothée Lesort … David FilliatarXiv
    PDF ↗
  22. 2019
    Marginal Replay vs Conditional Replay for Continual LearningTimothée Lesort, Alexander Gepperth, Andrei Stoian, David FilliatSpringer LNCS · École Nationale Supérieure de Techniques Avancées · Thales (France) · +1
    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. 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.