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.

4,574 papers · showing 3501–3550Sort Recent · Most cited
  1. 2022
    DualPrompt: Complementary Prompting for Rehearsal-free Continual LearningZifeng Wang, Zizhao Zhang, Sayna Ebrahimi … Tomas PfisterECCV
    PDF ↗
  2. 2022
    FOSTER: Feature Boosting and Compression for Class-Incremental LearningFuyun Wang, Da-Wei Zhou, Han-Jia Ye, De‐Chuan ZhanECCV
    PDF ↗
  3. 2022
    Information-theoretic Online Memory Selection for Continual LearningShengyang Sun, Daniele Calandriello, Huiyi Hu … Michalis K. TitsiasICLR
    PDF ↗
  4. 2022
    Introducing principles of synaptic integration in the optimization of deep neural networksGiorgia Dellaferrera, Stanisław Woźniak, Giacomo Indiveri … Evangelos EleftheriouNature Communications · University of Zurich · IBM Research - Zurich · +3
    PDF ↗
  5. 2022
    Incremental Prototype Tuning for Class Incremental LearningJie‐Ren Deng, Jianhua Hu, Haojian Zhang, Yunkuan WangarXiv
    PDF ↗
  6. 2022
    Efficient Test-Time Model Adaptation without ForgettingShuaicheng Niu, Jiaxiang Wu, Yifan Zhang … Mingkui TanICML
    PDF ↗
  7. 2022
    Revisiting a kNN-based Image Classification System with High-capacity StorageKengo Nakata, Youyang Ng, Daisuke Miyashita … Jun DeguchiECCV
    PDF ↗
  8. 2023
    Uncertainty-aware Contrastive Distillation for Incremental Semantic SegmentationGuanglei Yang, Enrico Fini, Dan Xu … Elisa RicciTPAMI · Harbin Institute of Technology · University of Trento · +2
    PDF ↗
  9. 2019
    Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set RecognitionMartin Mundt, Iuliia Pliushch, Sagnik Majumder … Visvanathan RameshJournal of Imaging · Goethe University Frankfurt · The University of Texas at Austin · +1
    PDF ↗
  10. 2022PDF ↗
  11. 2022PDF ↗
  12. 2020
    Instance Weighted Incremental Evolution Strategies for Reinforcement Learning in Dynamic EnvironmentsZhi Wang, Chunlin Chen, Daoyi DongTNNLS · University of Canberra · UNSW Sydney · +1
    PDF ↗
  13. 2022
    Gradient-Matching Coresets for Rehearsal-Based Continual LearningLukas Balles, Giovanni Zappella, Cédric ArchambeauarXiv
    PDF ↗
  14. 2022
    Stable Lifelong Learning: Spiking neurons as a solution to instability in plastic neural networksSamuel Schmidgall, Joe HaysNeuro-Inspired Computational Elements Conference · United States Naval Research Laboratory
    PDF ↗
  15. 2022PDF ↗
  16. 2022
    Continual Learning and Private UnlearningBo Liu, Qiang Liu, Peter StoneCoLLAs
    PDF ↗
  17. 2022PDF ↗
  18. 2022
    Is Class-Incremental Enough for Continual Learning?Andrea Cossu, Gabriele Graffieti, Lorenzo Pellegrini … Vincenzo LomonacoFrontiers · University of Pisa · Scuola Normale Superiore · +1
    PDF ↗
  19. 2022
    Addressing Client Drift in Federated Continual Learning with Adaptive OptimizationYeshwanth Venkatesha, Youngeun Kim, Hyoungseob Park … Priyadarshini PandaarXiv
    PDF ↗
  20. 2022
    Tackling Online One-Class Incremental Learning by Removing Negative ContrastsNader Asadi, Sudhir P. Mudur, Eugene BelilovskyarXiv
    PDF ↗
  21. 2022
    Biological underpinnings for lifelong learning machinesDhireesha Kudithipudi, Mario Aguilar-Simon, Jonathan Babb … Hava T. SiegelmannNature Machine Intelligence · The University of Texas at San Antonio · Intelligent Systems Research (United States) · +24
    PDF ↗
  22. 2022
    The Challenges of Continuous Self-Supervised LearningSenthil Purushwalkam, Pedro Morgado, Abhinav GuptaECCV
    PDF ↗
  23. 2022
    Resonance in Weight Space: Covariate Shift Can Drive Divergence of SGD with MomentumKirby Banman, Liam Peet-Pare, Nidhi Hegde … Martha WhiteICLR
    PDF ↗
  24. 2022
    Online Continual Learning for Embedded DevicesTyler L. Hayes, Christopher KananCoLLAs
    PDF ↗
  25. 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 ↗
  26. 2022PDF ↗
  27. 2022
    A Closer Look at Knowledge Distillation with Features, Logits, and GradientsYen-Chang Hsu, James Smith, Yilin Shen … Hongxia JinarXiv
    PDF ↗
  28. 2020
    Self-Training for Class-Incremental Semantic SegmentationLu Yu, Xialei Liu, Joost van de WeijerTNNLS · Tianjin University of Technology · Nankai University · +1
    PDF ↗
  29. 2022
    ConTinTin: Continual Learning from Task InstructionsWenpeng Yin, Jia Li, Caiming XiongACL
    PDF ↗
  30. 2022PDF ↗
  31. 2022
    L2Explorer: A Lifelong Reinforcement Learning Assessment EnvironmentErik C. Johnson, Eric Q. Nguyen, Blake A. Schreurs … Gautam K. VallabhaarXiv
    PDF ↗
  32. 2022
    Continual Prompt Tuning for Dialog State TrackingQi Zhu, Bing Li, Fei Mi … Minlie HuangACL
    PDF ↗
  33. 2022
    Sequential changepoint detection in neural networks with checkpointsMichalis K. Titsias, Jakub Sygnowski, Yutian ChenStatistics and Computing · Google DeepMind (United Kingdom)
    PDF ↗
  34. 2022
    ELLE: Efficient Lifelong Pre-training for Emerging DataYujia Qin, Jiajie Zhang, Yankai Lin … Jie ZhouACL
    PDF ↗
  35. 2022
    Sparsity and Heterogeneous Dropout for Continual Learning in the Null Space of Neural ActivationsAli Abbasi, Parsa Nooralinejad, Vladimir Braverman … Soheil KolouriCoLLAs
    PDF ↗
  36. 2022
    Mind Your Manners! A Dataset and a Continual Learning Approach for Assessing Social Appropriateness of Robot ActionsJonas Tjomsland, Sinan Kalkan, Hatice GüneşFrontiers · University of Cambridge · Middle East Technical University
    PDF ↗
  37. 2022
    Controlling Soft Robotic Arms Using Continual LearningFrancesco Piqué, Hari Teja Kalidindi, Lorenzo Fruzzetti … Egidio FaloticoRA-L · Scuola Superiore Sant'Anna · National University of Singapore
    PDF ↗
  38. 2022PDF ↗
  39. 2022
    Lifelong 3D Object Recognition and Grasp Synthesis Using Dual Memory Recurrent Self-Organization NetworksKrishnakumar Santhakumar, Hamidreza KasaeiNeural Networks · University of Groningen
    PDF ↗
  40. 2022PDF ↗
  41. 2022
    Acceleration of Federated Learning with Alleviated Forgetting in Local TrainingChencheng Xu, Zhiwei Hong, Minlie Huang, Tao JiangICLR
    PDF ↗
  42. 2022PDF ↗
  43. 2022
    Provable and Efficient Continual Representation LearningYingcong Li, Mingchen Li, M. Salman Asif, Samet OymakarXiv
    PDF ↗
  44. 2020
    Efficient Architecture Search for Continual LearningQiang Gao, Zhipeng Luo, Diego Klabjan, Fengli ZhangTNNLS · Southwestern University of Finance and Economics · Northwestern University · +1
    PDF ↗
  45. 2022PDF ↗
  46. 2022
    Continual Learning of Multi-modal Dynamics with External MemoryAbdullah Akgül, Gözde Ünal, Melih KandemirConference on Learning for Dynamics & Control · University of Southern Denmark · Istanbul Technical University
    PDF ↗
  47. 2022
    A Versatile Agent for Fast Learning from Human InstructorsYiwen Chen, Zedong Zhang, Haofeng Liu … Marcelo H. AngarXiv
    PDF ↗
  48. 2023
    Learning Fast and Slow for Online Time Series ForecastingQuang Pham, Chenghao Liu, Doyen Sahoo, Steven C. H. HoiICLR
    PDF ↗
  49. 2022
    BERT WEAVER: Using WEight AVERaging to Enable Lifelong Learning for Transformer-based ModelsKühnel, Lisa, Alexander Schulz, Barbara Hammer, Juliane FluckarXiv
    PDF ↗
  50. 2023
    Continual Learning Beyond a Single ModelThang Doan, Seyed Iman Mirzadeh, Mehrdad FarajtabarCoLLAs
    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.