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.

505 papers of 4,574 · showing 1–50Sort Recent · Most cited
  1. 2022
    Unveiling the Tapestry: The Interplay of Generalization and Forgetting in Continual LearningZenglin Shi, Jie Jing, Ying Sun … Mengmi ZhangTNNLS · Nanyang Technological University · Agency for Science, Technology and Research
    PDF ↗
  2. 2022
    Exemplar-Free Continual Learning of Vision Transformers via Gated Class-Attention and Cascaded Feature Drift CompensationMarco Cotogni, Fei Yang, Claudio Cusano … Joost van de WeijerIJCV · University of Pavia · BGI Group (China) · +4
    PDF ↗
  3. 2022
    CL-Cross VQA: A Continual Learning Benchmark for Cross-Domain Visual Question AnsweringYao Zhang, Haokun Chen, Ahmed Frikha … Volker TrespWACV · LMU Klinikum · Ludwig-Maximilians-Universität München · +1
    PDF ↗
  4. 2022
    MEIL-NeRF: Memory-Efficient Incremental Learning of Neural Radiance FieldsJaeyoung Chung, K. Lee, Sungyong Baik, Kyoung Mu LeeIEEE Access · Seoul National University · Hanyang University
    PDF ↗
  5. 2022
    Exploring the Intersection Between Neural Architecture Search and Continual LearningMohamed Shahawy, Elhadj Benkhelifa, David WhiteTNNLS · University of Staffordshire
    PDF ↗
  6. 2022
    Learning to Predict Gradients for Semi-Supervised Continual LearningYan Luo, Yongkang Wong, Mohan Kankanhalli, Qi ZhaoTNNLS · University of Minnesota · Harvard University · +2
    PDF ↗
  7. 2022
    Continual Learning via Sequential Function-Space Variational InferenceTim G. J. Rudner, Freddie Bickford Smith, Qixuan Feng … Yarin GalICML
    PDF ↗
  8. 2022
    AdaptCL: Adaptive Continual Learning for Tackling Heterogeneity in Sequential DatasetsYuqing Zhao, Divya Saxena, Jiannong CaoTNNLS · Hong Kong Polytechnic University
    PDF ↗
  9. 2022
    Probabilistic Bilevel Coreset SelectionXiaofang Zhou, Renjie Pi, Weizhong Zhang … Tong ZhangICML
    PDF ↗
  10. 2022
    Self-Activating Neural Ensembles for Continual Reinforcement LearningSam Powers, Xing, Eliot, Gupta, AbhinavCoLLAs · Carnegie Mellon University · Meta (Israel)
    PDF ↗
  11. 2022
    Complementary Calibration: Boosting General Continual Learning With Collaborative Distillation and Self-SupervisionZhong Ji, Jin Li, Qiang Wang, Zhongfei ZhangTIP · Tianjin University · Binghamton University
    PDF ↗
  12. 2022
    Hierarchically structured task-agnostic continual learningHeinke Hihn, Daniel BraunMachine Learning · Universität Ulm
    PDF ↗
  13. 2022
    Saliency-Augmented Memory Completion for Continual LearningGuangji Bai, Ling Chen, Yuyang Gao, Liang ZhaoSDM
    PDF ↗
  14. 2022
    Towards Continual Reinforcement Learning: A Review and PerspectivesKhimya Khetarpal, Matthew Riemer, Irina Rish, Doina PrecupJournal of Artificial Intelligence Research · Google DeepMind (United Kingdom) · McGill University · +2
    PDF ↗
  15. 2022
    Sleep-like unsupervised replay reduces catastrophic forgetting in artificial neural networksTimothy Tadros, Giri P. Krishnan, Ramyaa Ramyaa, Maxim BazhenovNature Communications · University of California San Diego · New Mexico Institute of Mining and Technology
    PDF ↗
  16. 2022
    DIODE: Dilatable Incremental Object DetectionCan Peng, Kun Zhao, Sam Maksoud … Brian C. LovellPattern Recognition · The University of Queensland
    PDF ↗
  17. 2022PDF ↗
  18. 2022
    G-MAP: General Memory-Augmented Pre-trained Language Model for Domain TasksZhongwei Wan, Yichun Yin, Wei Zhang … Liu, QunEMNLP
    PDF ↗
  19. 2022
    Open World DETR: Transformer based Open World Object DetectionNa Dong, Yongqiang Zhang, Mingli Ding, Gim Hee LeearXiv
    PDF ↗
  20. 2022
    Evidential Deep Learning for Class-Incremental Semantic SegmentationKarl Holmquist, Lena M. Klasen, Michael FelsbergScandinavian Conference on Image Analysis
    PDF ↗
  21. 2022PDF ↗
  22. 2022
    Three types of incremental learningGido M. van de Ven, Tinne Tuytelaars, Andreas S. ToliasNature Machine Intelligence · Baylor College of Medicine · University of Cambridge · +2
    PDF ↗
  23. 2022
    DA-CIL: Towards Domain Adaptive Class-Incremental 3D Object DetectionZiyuan Zhao, Mingxi Xu, Peisheng Qian … Richard ChangBMVC
    PDF ↗
  24. 2022
    A Hybrid Active-Passive Approach to Imbalanced Nonstationary Data Stream ClassificationKleanthis Malialis, Manuel Roveri, Cesare Alippi … Marios M. PolycarpouIEEE Symposium Series on Computational Intelligence (SSCI) · University of Cyprus · Politecnico di Milano
    PDF ↗
  25. 2022PDF ↗
  26. 2022
    Continual Learning with Distributed Optimization: Does CoCoA Forget Under Task Repetition?Martin Hellkvist, Ayça Özçelikkale, Anders ÅhlénEuropean Signal Processing Conference
    PDF ↗
  27. 2022
    The geometry of representational drift in natural and artificial neural networksKyle Aitken, Marina Garrett, Shawn R. Olsen, Ştefan MihalaşPLOS · Allen Institute
    PDF ↗
  28. 2022
    Progressive Learning without ForgettingTao Feng, Hangjie Yuan, Mang Wang … Jianzhou ZhangarXiv
    PDF ↗
  29. 2022
    Neural Architecture for Online Ensemble Continual LearningMateusz Wójcik, Witold Kościukiewicz, Tomasz Kajdanowicz, Adam GonczarekarXiv
    PDF ↗
  30. 2022
    Wild-Time: A Benchmark of in-the-Wild Distribution Shift over TimeHuaxiu Yao, Caroline Choi, Bochuan Cao … Chelsea FinnNeurIPS
    PDF ↗
  31. 2022PDF ↗
  32. 2022
    Semi-Supervised Lifelong Language LearningYingxiu Zhao, Yinhe Zheng, Bowen Yu … Nevin L. ZhangEMNLP
    PDF ↗
  33. 2022
    Integral Continual Learning Along the Tangent Vector Field of TasksTian Yu Liu, Aditya Golatkar, Stefano Soatto, Alessandro AchillearXiv
    PDF ↗
  34. 2022
    Delving into Transformer for Incremental Semantic SegmentationZekai Xu, Mingyi Zhang, Jiayue Hou … Junge ZhangarXiv
    PDF ↗
  35. 2022
    Bayesian continual learning via spiking neural networksNicolas Skatchkovsky, Hyeryung Jang, Osvaldo SimeoneFrontiers · King's College London · Dongguk University
    PDF ↗
  36. 2022
    Brain-inspired Predictive Coding Improves the Performance of Machine Challenging TasksJangho Lee, Jeonghee Jo, Byoung-Hwa Lee … Sungroh YoonFrontiers · Seoul National University · Electronics and Telecommunications Research Institute · +1
    PDF ↗
  37. 2022
    Mining Unseen Classes via Regional Objectness: A Simple Baseline for Incremental SegmentationZekang Zhang, Guangyu Gao, Zhiyuan Fang … Yunchao WeiNeurIPS
    PDF ↗
  38. 2022PDF ↗
  39. 2022
    LLEDA - Lifelong Self-Supervised Domain AdaptationMamatha Thota, Dewei Yi, Georgios LeontidisKnowledge-Based Systems
    PDF ↗
  40. 2022PDF ↗
  41. 2022PDF ↗
  42. 2022
    Cold Start Streaming Learning for Deep NetworksC. Wolfe, Anastasios KyrillidisarXiv
    PDF ↗
  43. 2022
    Learning For Predictive Control: A Dual Gaussian Process ApproachYuhan Liu, Pengyu Wang, Roland Tóthat - Automatisierungstechnik
    PDF ↗
  44. 2022PDF ↗
  45. 2022
    A Theoretical Study on Solving Continual LearningGyuhak Kim, Changnan Xiao, Tatsuya Konishi … Bing LiuNeurIPS
    PDF ↗
  46. 2022PDF ↗
  47. 2022
    Overcoming Barriers to Skill Injection in Language Modeling: Case Study in ArithmeticMandar Sharma, Nikhil Muralidhar, Naren RamakrishnanarXiv
    PDF ↗
  48. 2022
    Learning a Condensed Frame for Memory-Efficient Video Class-Incremental LearningYixuan Pei, Zhiwu Qing, Jun Cen … Xueming QianNeurIPS
    PDF ↗
  49. 2022
    Beyond Not-Forgetting: Continual Learning with Backward Knowledge TransferSen Lin, Li Yang, Deliang Fan, Junshan ZhangNeurIPS
    PDF ↗
  50. 2022
    An analytical theory of curriculum learning in teacher–student networksLuca Saglietti, Stefano Sarao Mannelli, Andrew SaxeNeurIPS · Bocconi University · Gatsby Computational Neuroscience Unit · +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, 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.