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.

18 papers of 6,984Sort Recent · Most cited
  1. 2025
    Learning by Taking Notes: Memory-Guided Continual Learning for Generative Multimodal ModelsYanhui Guo, Cai-fang Guo, Yan Gao, Yi SunICCV · Amazon (United States)
  2. 2025
    A Survey on Knowledge Editing of Neural NetworksVittorio Mazzia, Alessandro Pedrani, Andrea Caciolai … Davide BernardiTNNLS · Amazon (United States)
    PDF ↗
  3. 2024
    Canonical Shape Projection Is All You Need for 3D Few-Shot Class Incremental LearningAli Cheraghian, Zeeshan Hayder, Sameera Ramasinghe … Mehrtash HarandiECCV · Australian National University · Commonwealth Scientific and Industrial Research Organisation · +6
  4. 2023
    Quantifying Catastrophic Forgetting in Continual Federated LearningChristophe Dupuy, Jimit Majmudar, Jixuan Wang … Salman AvestimehrICASSP · Amazon (United States) · University of Southern California · +1
  5. 2023
    Federated Self-Learning with Weak Supervision for Speech RecognitionMilind Rao, Gopinath Chennupati, Gautam Tiwari … Jasha DroppoICASSP · Amazon (United States)
    PDF ↗
  6. 2023
    Large-scale Lifelong Learning of In-context Instructions and How to Tackle ItJisoo Mok, Jaeyoung Do, Sung‐Jin Lee … Sungroh YoonACL · Seoul National University · New Generation University College · +4
    PDF ↗
  7. 2022
    Preventing Catastrophic Forgetting in Continual Learning of New Natural Language TasksSudipta Kar, Giuseppe Castellucci, Simone Filice … Oleg RokhlenkoKDD · Amazon (United States)
    PDF ↗
  8. 2022
    ILASR: Privacy-Preserving Incremental Learning for Automatic Speech Recognition at Production ScaleGopinath Chennupati, Milind Rao, Gurpreet Chadha … Pankaj SitpureKDD · Amazon (United States)
    PDF ↗
  9. 2022
    Overcoming Catastrophic Forgetting During Domain Adaptation of Seq2seq Language GenerationDingcheng Li, Zheng Chen, Eunah Cho … Yang LiuNAACL · Amazon (United States)
  10. 2022
    Learning Representations for New Sound Classes With Continual Self-Supervised LearningZhepei Wang, Cem Subakan, Xilin Jiang … Paris SmaragdisIEEE Signal Processing Letters · University of Illinois Urbana-Champaign · Concordia University · +2
    PDF ↗
  11. 2021
    SynthASR: Unlocking Synthetic Data for Speech RecognitionAmin Fazel, Wei Yang, Yulan Liu … Jasha DroppoInterspeech · Samsung (South Korea) · Amazon (United States) · +1
    PDF ↗
  12. 2021
    CIFDM: Continual and Interactive Feature Distillation for Multi-Label Stream LearningYigong Wang, Zhuoyi Wang, Yu Lin … Dingcheng LiSIGIR · The University of Texas at Dallas · Amazon (United States)
  13. 2021
    CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification TasksZixuan Ke, Bing Liu, Hu Xu, Lei ShuEMNLP · University of Illinois Chicago · Meta (Israel) · +1
    PDF ↗
  14. 2021
    Lifelong Event Detection with Knowledge TransferPengfei Yu, Heng Ji, Prem NatarajanEMNLP · University of Illinois Urbana-Champaign · Amazon (United States)
    PDF ↗
  15. 2020
    Learning to Solve NLP Tasks in an Incremental Number of LanguagesGiuseppe Castellucci, Simone Filice, Danilo Croce, Roberto BasiliACL · Amazon (United States) · Seattle University · +3
  16. 2020
    Incremental Few-Shot Meta-learning via Indirect Discriminant AlignmentQing Liu, Orchid Majumder, Alessandro Achille … Stefano SoattoECCV · Johns Hopkins University · Amazon (United States)
  17. 2020
    An Empirical Investigation towards Efficient Multi-Domain Language Model Pre-trainingKristjan Arumae, Qing Sun, Parminder BhatiaEMNLP · Amazon (United States) · Seattle University · +1
    PDF ↗
  18. 2020
    M2KD: Incremental Learning via Multi-model and Multi-level Knowledge DistillationPeng Zhou, Long Mai, Jianming Zhang … Larry S. DavisBMVC · Beth Israel Deaconess Medical Center · Adobe Systems (United States) · +2
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.