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.

27 papers of 5,456Sort Recent · Most cited
  1. 2023
    Towards Robust Graph Incremental Learning on Evolving GraphsJunwei Su, Difan Zou, Zijun Zhang, Chuan WuICML
    PDF ↗
  2. 2023
    Do You Remember? Overcoming Catastrophic Forgetting for Fake Audio DetectionXiaohui Zhang, Jiangyan Yi, Jianhua Tao … Chuyuan ZhangICML
    PDF ↗
  3. 2023
    Learning Expressive Priors for Generalization and Uncertainty Estimation in Neural NetworksDominik Schnaus, Jong‐Seok Lee, Daniel Cremers, Rudolph TriebelICML
    PDF ↗
  4. 2023
    Parameter-Level Soft-Masking for Continual LearningTatsuya Konishi, Mori Kurokawa, Chihiro Ono … Bing LiuICML
    PDF ↗
  5. 2023
    Learnability and Algorithm for Continual LearningGyuhak Kim, Changnan Xiao, Tatsuya Konishi, Bing LiuICML
    PDF ↗
  6. 2023
    Continual Learners are Incremental Model GeneralizersJaehong Yoon, Sung Ju Hwang, Yue CaoICML
    PDF ↗
  7. 2023
    Continual Learning in Linear Classification on Separable DataItay Evron, Edward Moroshko, Gon Buzaglo … Daniel SoudryICML
    PDF ↗
  8. 2023
    Memory-Based Dual Gaussian Processes for Sequential LearningPaul E. Chang, Prakhar Verma, St. John … Mohammad Emtiyaz KhanICML
    PDF ↗
  9. 2023
    Continual Task Allocation in Meta-Policy Network via Sparse PromptingYijun Yang, Tianyi Zhou, Jing Jiang … Yuhui ShiICML
    PDF ↗
  10. 2023
    Lifelong Language Pretraining with Distribution-Specialized ExpertsWuyang Chen, Yanqi Zhou, Nan Du … C. C. Iuras ̧cuICML
    PDF ↗
  11. 2023PDF ↗
  12. 2023
    BiRT: Bio-inspired Replay in Vision Transformers for Continual LearningKishaan Jeeveswaran, Prashant Bhat, Bahram Zonooz, Elahe AraniICML
    PDF ↗
  13. 2023
    DualHSIC: HSIC-Bottleneck and Alignment for Continual LearningZifeng Wang, Zheng Zhan, Yifan Gong … Jennifer DyICML
    PDF ↗
  14. 2023
    The Ideal Continual Learner: An Agent That Never ForgetsLiangzu Peng, Paris V. Giampouras, René VidalICML
    PDF ↗
  15. 2023
    Does Continual Learning Equally Forget All Parameters?Haiyan Zhao, Tianyi Zhou, Guodong Long … Chengqi ZhangICML
    PDF ↗
  16. 2023
    Prototype-Sample Relation Distillation: Towards Replay-Free Continual LearningNader Asadi, MohammadReza Davar, Sudhir P. Mudur … Eugene BelilovskyICML
    PDF ↗
  17. 2023
    Understanding plasticity in neural networksClare Lyle, Zeyu Zheng, Evgenii Nikishin … Will DabneyICML
    PDF ↗
  18. 2023
    Task-Specific Skill Localization in Fine-tuned Language ModelsAbhishek Panigrahi, Nikunj Saunshi, Haoyu Zhao, Sanjeev AroraICML
    PDF ↗
  19. 2023
    Theory on Forgetting and Generalization of Continual LearningSen Lin, Peizhong Ju, Yingbin Liang, Ness B. ShroffICML
    PDF ↗
  20. 2023
    Exploring the Benefits of Training Expert Language Models over Instruction TuningJoel Jang, Seungone Kim, Seonghyeon Ye … Minjoon SeoICML
    PDF ↗
  21. 2023
    Efficient Parametric Approximations of Neural Network Function Space DistanceNikita Dhawan, Sicong Huang, Juhan Bae, Roger GrosseICML
    PDF ↗
  22. 2023
    Neuro Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept RehearsalEmanuele Marconato, Gianpaolo Bontempo, Elisa Ficarra … Stefano TesoICML
    PDF ↗
  23. 2023PDF ↗
  24. 2023
  25. 2023
    Optimizing Mode Connectivity for Class Incremental LearningHaitao Wen, Haoyang Cheng, Heqian Qiu … Hongliang LiICML
  26. 2023
  27. 2023
    Discrete Key-Value BottleneckFrederik Träuble, Anirudh Goyal, Nasim Rahaman … Bernhard SchölkopfICML
    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.