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.

37 papers of 6,984Sort Recent · Most cited
  1. 2024
    Accurate Forgetting for Heterogeneous Federated Continual LearningAbudukelimu Wuerkaixi, Sen Cui, Jingfeng Zhang … Masashi SugiyamaICLR
    PDF ↗
  2. 2024PDF ↗
  3. 2024PDF ↗
  4. 2024
    Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained ComputationWenxuan Zhang, Youssef Mohamed, Bernard Ghanem … Mohamed ElhoseinyICLR
    PDF ↗
  5. 2024
    Scalable Language Model with Generalized Continual LearningBohao Peng, Zhuotao Tian, Shu Liu … Jiaya JiaICLR
    PDF ↗
  6. 2024PDF ↗
  7. 2024PDF ↗
  8. 2024
    A Unified and General Framework for Continual LearningZhenyi Wang, Yan Li, Li Shen, Heng HuangICLR
    PDF ↗
  9. 2024
    Function-space Parameterization of Neural Networks for Sequential LearningAidan Scannell, Riccardo Mereu, Paul E. Chang … Arno SolinICLR
    PDF ↗
  10. 2024PDF ↗
  11. 2024
    Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural NetworksMingqing Xiao, Qingyan Meng, Zongpeng Zhang … Zhouchen LinICLR
    PDF ↗
  12. 2024
    Elastic Feature Consolidation for Cold Start Exemplar-free Incremental LearningSimone Magistri, Tomaso Trinci, Albin Soutif--Cormerais … Andrew D. BagdanovICLR
    PDF ↗
  13. 2024PDF ↗
  14. 2024PDF ↗
  15. 2024
    Locality Sensitive Sparse Encoding for Learning World Models OnlineZichen Liu, Chao Du, Wee Sun Lee, Min LinICLR
    PDF ↗
  16. 2024
    Divide and not forget: Ensemble of selectively trained experts in Continual LearningGrzegorz Rypeść, Sebastian Cygert, Valeriya Khan … Bartłomiej TwardowskiICLR · Warsaw University of Technology · Integrated Detector Electronics AS (Norway) · +6
    PDF ↗
  17. 2024
    Prompt Gradient Projection for Continual LearningJingyang Qiao, Zhizhong Zhang, Xin Tan … Yuan XieICLR
  18. 2024
  19. 2024
  20. 2024
  21. 2024
  22. 2024
  23. 2024
  24. 2024
  25. 2024
  26. 2024
  27. 2024
    TiC-CLIP: Continual Training of CLIP ModelsSaurabh Garg, Mehrdad Farajtabar, Hadi Pouransari … Fartash FaghriICLR
    PDF ↗
  28. 2024
    TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained ModelsZuxin Liu, Jesse Zhang, Kavosh Asadi … Rasool FakoorICLR
    PDF ↗
  29. 2024
    TRAM: Bridging Trust Regions and Sharpness Aware MinimizationTom Sherborne, Naomi Saphra, Pradeep Dasigi, Hao PengICLR
    PDF ↗
  30. 2024
    Class Incremental Learning via Likelihood Ratio Based Task PredictionHaowei Lin, Yijia Shao, Weinan Qian … Bing LiuICLR
    PDF ↗
  31. 2024
    Understanding Catastrophic Forgetting in Language Models via Implicit InferenceSuhas Kotha, Jacob M. Springer, Aditi RaghunathanICLR
    PDF ↗
  32. 2024
    Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated LearningYavuz Faruk Bakman, Duygu Nur Yaldiz, Yahya H. Ezzeldin, Salman AvestimehrICLR
    PDF ↗
  33. 2024
    Progressive Fourier Neural Representation for Sequential Video CompilationHaeyong Kang, Jaehong Yoon, DaHyun Kim … Chang D. YooICLR
    PDF ↗
  34. 2024
    Kalman Filter for Online Classification of Non-Stationary DataMichalis K. Titsias, Alexandre Galashov, Amal Rannen-Triki … Jörg BornscheinICLR
    PDF ↗
  35. 2024
    A Probabilistic Framework for Modular Continual LearningLazar Valkov, Akash Srivastava, Swarat Chaudhuri, Charles SuttonICLR
    PDF ↗
  36. 2024
    ViDA: Homeostatic Visual Domain Adapter for Continual Test Time AdaptationJiaming Liu, Senqiao Yang, Peidong Jia … Shanghang ZhangICLR
    PDF ↗
  37. 2024
    Prediction Error-based Classification for Class-Incremental LearningMichał Zając, Tinne Tuytelaars, Gido M. van de VenICLR
    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.