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.

16 papers of 6,984Sort Recent · Most cited
  1. 2026
    Dream2Learn: Structured Generative Dreaming for Continual LearningSalvatore Calcagno, Matteo Pennisi, Federica Proietto Salanitri … Giovanni BellittoIJCV · University of Catania
    PDF ↗
  2. 2026
    Bi-Compatible Task-Agnostic Feature Augmentation for Expansion-Based Class-Incremental LearningBowen Zheng, Zijun Shen, Da-Wei Zhou … De‐Chuan ZhanIJCV · Nanjing University
  3. 2026
    Sample-Aware Knowledge Association and Enhancement for Open-Vocabulary Continual LearningZhilin Zhu, Zhiheng Ma, Yabin Wang … Xiaopeng HongIJCV · Harbin Institute of Technology · Peng Cheng Laboratory · +2
  4. 2026
    Sparse Orthogonal Parameters Tuning for Continual LearningKun-Peng Ning, Hai-Jian Ke, Yuyang Liu … Yuan LiIJCV · Peking University Shenzhen Hospital · Peng Cheng Laboratory
    PDF ↗
  5. 2026
    EKPC: Elastic Knowledge Preservation and Compensation for Class-Incremental LearningHuaijie Wang, De Cheng, Lingfeng He … Xinbo GaoIJCV · Xidian University · Northwestern Polytechnical University
    PDF ↗
  6. 2026
    ReBac: Current-to-Past Residual Background Correction for Class-Incremental Semantic SegmentationGuangyu Gao, Anqi Zhang, Jianbo Jiao … Yunchao WeiIJCV · Beijing Institute of Technology · University of Birmingham · +1
  7. 2023
    Teacher Agent: A Knowledge Distillation-Free Framework for Rehearsal-Based Video Incremental LearningShengqin Jiang, Yaoyu Fang, Haokui Zhang … Peng WangIJCV · Nanjing University of Information Science and Technology · Northwestern Polytechnical University · +3
    PDF ↗
  8. 2026
    Vision-Language Efficient Tuning for Mitigating Catastrophic Forgetting in Multi-Modal LearningYaoming Wang, Yuchen Liu, Wenrui Dai … Hongkai XiongIJCV · Shanghai Jiao Tong University · Huawei Technologies (China)
  9. 2026PDF ↗
  10. 2026
    COBRA: A Continual Learning Approach to Vision-Brain UnderstandingXuan-Bac Nguyen, Manuel Serna-Aguilera, Arabinda K. Choudhary … Ky LuuIJCV · University of Arkansas at Fayetteville · SUNY Upstate Medical University · +2
    PDF ↗
  11. 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 ↗
  12. 2025
    Relation-Guided Adversarial Learning for Data-Free Knowledge TransferYingping Liang, Ying FuIJCV · Beijing Institute of Technology
    PDF ↗
  13. 2025
    Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You NeedDa-Wei Zhou, Zi-Wen Cai, Han-Jia Ye … Ziwei LiuIJCV · Nanjing University · Nanyang Technological University
    PDF ↗
  14. 2024
    Towards Non Co-occurrence Incremental Object Detection with Unlabeled In-the-Wild DataNa Dong, Yongqiang Zhang, Mingli Ding, Gim Hee LeeIJCV · Harbin Institute of Technology · National University of Singapore
  15. 2024
  16. 2023
    Trust-Region Adaptive Frequency for Online Continual LearningYajing Kong, Liu Liu, Maoying Qiao … Dacheng TaoIJCV · The University of Sydney · University of Technology Sydney
    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.