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.

761 papers of 4,574 · showing 101–150Sort Recent · Most cited
  1. 2026
    Rethinking Transfer in Continual Learning: A Replay-Based RealisationYang Meng, Zhenya Liu, Zhuokai Zhao, Yuxin ChenarXiv
    PDF ↗
  2. 2026PDF ↗
  3. 2026PDF ↗
  4. 2026
    Parameter-Efficient Continual Fine-Tuning: A SurveyE N Coleman, Luigi Quarantiello, Ziyue Liu … Vincenzo LomonacoNeurocomputing · University of Pisa · Politecnico di Torino · +4
    PDF ↗
  5. 2026PDF ↗
  6. 2026PDF ↗
  7. 2026
    FedGRAIL: Trustworthy and Efficient Federated Class-Incremental Learning for Long-Tailed IoT Edge IntelligenceXinrong Gong, Zibin Ke, Dan Dai … Kaixiang YangIEEE Internet of Things Journal
    PDF ↗
  8. 2026
    StructAlign: Structured Cross-Modal Alignment for Continual Text-to-Video RetrievalShaokun Wang, Weili Guan, Jizhou Han … Liqiang NieSIGIR · Harbin Institute of Technology · Shenzhen Institute of Information Technology · +2
    PDF ↗
  9. 2026
    SymbOmni: Evolving Agentic Omni Models via Symbolic Concept LearningJinxiu Liu, Jianru Li, Tanqing Kuang … Weiyang LiuarXiv
    PDF ↗
  10. 2026
    Continual Evolution Strategies in Control TasksNICOLA PITZALIS, Eleni Nisioti, Antonio Carta … Andrea CossuGenetic and Evolutionary Computation Conference Companion · University of Pisa · IT University of Copenhagen
    PDF ↗
  11. 2026PDF ↗
  12. 2026
    Hybrid Continual Learning for Low-Resource Australian Aboriginal Language IdentificationPravina Mylvaganam, Ting Dang, Eliathamby Ambikairajah … Jingyao WuarXiv
    PDF ↗
  13. 2026
    UNIT: Unleash Large Language Models Potential for Graph Continual LearningTairan Huang, Yili Wang, Beibei Hu … Jianliang GaoarXiv
    PDF ↗
  14. 2026
    A Parametric Memory Head for Continual Generative RetrievalKidist Amde Mekonnen, Yubao Tang, Maarten de RijkeSIGIR · Amsterdam University of the Arts · University of Amsterdam
    PDF ↗
  15. 2026
    COvolve: Adversarial Co-Evolution of Large-Language-Model-Generated Policies and Environments via Two-Player Zero-Sum GameAlkis Sygkounas, Rishi Hazra, Andreas Persson … Amy LoutfiGenetic and Evolutionary Computation Conference · Örebro University
    PDF ↗
  16. 2026
    Multi-Faceted Continual Knowledge Graph Embedding for Semantic-Aware Link PredictionJing Qi, Yuxiang Wang, Zhiyuan Yu … Tianxing WuSIGIR · Hangzhou Dianzi University · Xidian University · +1
    PDF ↗
  17. 2026
    Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future DirectionsSarthak Kumar Maharana, Shambhavi Mishra, Yunbei Zhang … Yunhui GuoTMLR
    PDF ↗
  18. 2026
    When Does Continual Learning Require LearningAnne Harrington, Nayan Saxena, Michael Murphy … Yutong BaiarXiv
    PDF ↗
  19. 2026
    Lifelong Representations: A Survey on Continual Self-Supervised Learning for Vision ModelsSergi Masip, Alicja Dobrzeniecka, Jonathan Swinnen … Tinne TuytelaarsarXiv
    PDF ↗
  20. 2026
    Learning Probabilistic Prompt for Continual LearningHye-Kang Park, Sanghoon Lee, Geon Lee … Bumsub HamarXiv
    PDF ↗
  21. 2026PDF ↗
  22. 2026
    To Retain or to Adapt? Generalizing Continual LearningGiulia Lanzillotta, Mandana Samiei, Doina Precup … Claire VernadearXiv
    PDF ↗
  23. 2026
    RL Forgets! Towards Continual Policy OptimizationMao-Lin Luo, Zhe-Xu Wang, Zi-Hao Zhou … Tong WeiarXiv
    PDF ↗
  24. 2026PDF ↗
  25. 2026PDF ↗
  26. 2026PDF ↗
  27. 2026PDF ↗
  28. 2026PDF ↗
  29. 2026PDF ↗
  30. 2026PDF ↗
  31. 2026PDF ↗
  32. 2026PDF ↗
  33. 2026
    Challenges of Explainability in Continual Learning for Time Series ForecastingQuentin Besnard, Emmanuel Doumard, Nicolas Labroche … Nicolas RinguetEDBT/ICDT Workshops · Institute of Chartered Financial Analysts of India · 3D Technology Laboratories (United States) · +1
    PDF ↗
  34. 2026
    Rosetta: Composable Native Multimodal PretrainingXiangyue Liu, Zijian Zhang, Miles Yang … Ping TanarXiv
    PDF ↗
  35. 2026PDF ↗
  36. 2026PDF ↗
  37. 2026
    SUM: Unified Geometric Surgery on Spatio-Temporal Adaptation Vectors for Federated Class Incremental LearningJaeik Kim, Jaeyoung DoarXiv · Seoul National University · Seoul National University of Education · +1
    PDF ↗
  38. 2026
    Wake up for Touch! Mask-isolated Tactile Alignment Learning in MLLMsYoonhyung Park, Minji Kim, Sungwon Moon, Jiyoung LeearXiv
    PDF ↗
  39. 2026
    ASPIRE: Agentic /Skills Discovery for RoboticsRunyu Lu, Yubo Wu, Ethan Kou … Guanzhi WangarXiv
    PDF ↗
  40. 2026PDF ↗
  41. 2026PDF ↗
  42. 2026
    Convergence of Continual Learning in Homogeneous Deep NetworksMatan Schliserman, Gon Buzaglo, Itay Evron, Daniel SoudryCOLT
    PDF ↗
  43. 2026
    Few-Shot Domain Incremental Learning via Continual Vision-Language ConsolidationNaeem Paeedeh, Mahardhika Pratama, Wolfgang Mayer … Yew-Soon OngarXiv
    PDF ↗
  44. 2026
    Multisensory Continual Learning: Adapting Pretrained Visuomotor Policies to ForceJaden Clark, Changhao Wang, Yihuai Gao … Shuran SongarXiv
    PDF ↗
  45. 2026PDF ↗
  46. 2026
    Prototype Latent World Model Replay for Class-Incremental LearningWeizhi Nie, Hui Wang, Weijie Wang, Yuting SuarXiv
    PDF ↗
  47. 2026
    Fisher-Routed Mixture of Experts for Federated Class-Incremental LearningWenhao Yuan, Chenchen Lin, Jian Chen … Edith Cheuk Han NgaiarXiv
    PDF ↗
  48. 2026
    Transformer-Based Active Learning for Data-Efficient Vaccine Epitope Selection in PRRSAspen Erlandsson Brisebois, Zahed Khatooni, Connor Burbridge … Gordon BroderickarXiv
    PDF ↗
  49. 2026
    When One Adapter Speaks for Many: Discovering Low-Rank Redundancy in Continual Fine-TuningTanguy Dieudonné, Giulia Lanzillotta, Enis Simsar … Thomas HofmannarXiv
    PDF ↗
  50. 2026PDF ↗
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.