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.

960 papers of 4,574 · showing 51–100Sort Recent · Most cited
  1. 2025PDF ↗
  2. 2025PDF ↗
  3. 2025
    MoTiC: Momentum Tightness and Contrast for Few-Shot Class-Incremental LearningZeyu He, Shuai Huang, Yuwu Lu, Ming ZhaoPattern Recognition · Guilin University of Electronic Technology · South China Normal University
    PDF ↗
  4. 2025
    Annotation-Free Class-Incremental LearningKuchibhotla, Hari Chandana, Ananth, K S, Balasubramanian, Vineeth NarXiv
    PDF ↗
  5. 2025
    Condensation-Concatenation Framework for Dynamic Graph Continual LearningTingxu Yan, Y. Adam YuanInternational Symposium on Computer Engineering and Intel… · Southwest University
    PDF ↗
  6. 2025PDF ↗
  7. 2025PDF ↗
  8. 2025PDF ↗
  9. 2025PDF ↗
  10. 2025
    InTAct: Interval-based Task Activation Consolidation for Continual LearningPatryk Krukowski, Jan Miksa, Peter A. van der Helm … Przemysław SpurekarXiv
    PDF ↗
  11. 2025
    REAL: Representation Enhanced Analytic Learning for Exemplar-free Class-incremental LearningRun He, Di Fang, Yizhu Chen … Huiping ZhuangKnowledge-Based Systems · South China University of Technology · Hong Kong Polytechnic University
    PDF ↗
  12. 2025
    Multimodal Continual Instruction Tuning with Dynamic Gradient GuidanceLi, Songze, Gao, Mingyu, Su, Tonghua … Wang, ZhongjieCVPR
    PDF ↗
  13. 2025PDF ↗
  14. 2025
    Continual learning with a predictive coding based classifierSenhui Qiu, Saugat Bhattacharyya, Damien Coyle, Shirin DoraApplied Soft Computing · University of Ulster · Intelligent Systems Research (United States) · +2
    PDF ↗
  15. 2025
    Parameter Importance-Driven Continual Learning for Foundation ModelsWang, Lingxiang, Zhang, Hainan, Zheng, ZhimingarXiv
    PDF ↗
  16. 2025PDF ↗
  17. 2025PDF ↗
  18. 2025PDF ↗
  19. 2025
    Keeping Code-Aware LLMs Fresh: Full Refresh, In-Context Deltas, and Incremental Fine-TuningSharma, Pradeep Kumar, Puri, Ishaan, Singh, Mantinder Jit … Shrivastava, HritvikarXiv
    PDF ↗
  20. 2025PDF ↗
  21. 2025
    WebCoach: Self-Evolving Web Agents with Cross-Session Memory GuidanceGenglin Liu, Shijie Geng, Sha Li … Tianyi LiuarXiv
    PDF ↗
  22. 2025PDF ↗
  23. 2025
    Foundations of a Developmental Design Paradigm for Integrated Continual Learning, Deliberative Behavior, and ComprehensibilityZeki Doruk Erden, Boi FaltingsIEEE TETCI · École Polytechnique Fédérale de Lausanne
    PDF ↗
  24. 2025PDF ↗
  25. 2025
    Neuro-Logic Lifelong LearningBowen He, Xiaoan Xu, Alper Kamil Bozkurt … Juncheng DongarXiv
    PDF ↗
  26. 2025
    Teaching Prompts to Coordinate: Hierarchical Layer-Grouped Prompt Tuning for Continual LearningShengqin Jiang, T. Yung Kong, Yuankai Qi … Ming–Hsuan YangarXiv
    PDF ↗
  27. 2025
    Rethinking Class-Incremental Learning from a Dynamic Imbalanced Learning PerspectiveLeyuan Wang, Liuyu Xiang, Yunlong Wang … Zhaofeng HeIEEE Trans. Multimedia · Beijing University of Posts and Telecommunications · Chinese Academy of Sciences · +2
    PDF ↗
  28. 2025
    Preserving Cross-Modal Consistency for CLIP-based Class-Incremental LearningHaoran Chen, H. Y. Xu, Micah Goldblum … Wu, ZuxuanarXiv
    PDF ↗
  29. 2025PDF ↗
  30. 2025
    TT-LoRA MoE: Using Parameter-Efficient Fine-Tuning and Sparse Mixture-Of-ExpertsPradip Kunwar, Minh N. Vu, Maanak Gupta … Manish BhattaraiInternational Conference on Software Composition · Tennessee Technological University · Los Alamos National Laboratory · +1
    PDF ↗
  31. 2025
    Compact Memory for Continual Logistic RegressionYohan Jung, Hyungi Lee, Wenlong Chen … Mohammad Emtiyaz KhanNeurIPS
    PDF ↗
  32. 2025PDF ↗
  33. 2025PDF ↗
  34. 2025
    Hippocampal indexing alters the stability landscape of synaptic weight space allowing life-long learningOscar C. González, Ryan Golden, Erik Delanois … Maxim BazhenovbioRxiv · University of Colorado Boulder · University of California San Diego · +3
    PDF ↗
  35. 2025
    CEM: A Data-Efficient Method for Large Language Models to Continue Evolving From MistakesHaokun Zhao, Jinyi Han, Jie Shi … Fei YuCIKM · Fudan University · East China Normal University · +1
    PDF ↗
  36. 2025
    Continual Learning of Domain Knowledge from Human Feedback in Text-to-SQLThomas A. Cook, Patel, Kelly, Sivapriya Vellaichamy … Sumitra GanesharXiv
    PDF ↗
  37. 2025
    ExpReS-VLA: Specializing Vision-Language-Action Models Through Experience Replay and RetrievalShahram Najam Syed, Yatharth Ahuja, Arthur Jakobsson, Jeff IchnowskiarXiv
    PDF ↗
  38. 2025
    Mixtures of SubExperts for Large Language Continual LearningHaeyong Kang, Yoon, Hee Suk, Feng, Dahua, Yoo, Chang D.arXiv
    PDF ↗
  39. 2025
    Caption, Create, Continue: Continual Learning with Pre-trained Generative Vision-Language ModelsIndu Solomon, Aye Phyu Phyu Aung, Uttam Kumar, J. SenthilnathCIKM · International Institute of Information Technology Bangalore · Agency for Science, Technology and Research · +1
    PDF ↗
  40. 2025
    SEDEG:Sequential Enhancement of Decoder and Encoder's Generality for Class Incremental Learning with Small MemoryShaoling Pu, Hongyang Chen, Lingyu Zheng, Zhongwu SunSpringer CCIS · Zhejiang Lab · University of Chinese Academy of Sciences
    PDF ↗
  41. 2025
    Learn More, Forget Less: A Gradient-Aware Data Selection Approach for LLMLiu, Yibai, Shihang Wang, Liu, Zeming … Yunhong WangarXiv
    PDF ↗
  42. 2025
    Exploring the Tradeoff Between Diversity and Discrimination for Continuous Category DiscoveryRuobing Jiang, Yang Liu, Haobing Liu … Chunyang WangCIKM · Ocean University of China · East China Normal University
    PDF ↗
  43. 2025
    When Data Falls Short: Grokking Below the Critical ThresholdVaibhav Singh, Eugene Belilovsky, Rahaf AljundiarXiv
    PDF ↗
  44. 2025PDF ↗
  45. 2025
    Online Continual Learning on Intel Loihi 2 via a Co-designed Spiking Neural NetworkElvin Hajizada, Danielle Rager, Timothy Shea … Michael DaviesarXiv
    PDF ↗
  46. 2025
    Routing-Based Continual Learning for Multimodal Large Language ModelsMohta, Jay, Ak, Kenan Emir, Lee, Gwang … Shen, MingweiarXiv
    PDF ↗
  47. 2025
    A theory of initialisation’s impact on specialisationDevon Jarvis, Sebastian Lee, Clémentine Carla Juliette Dominé … Stefano Sarao MannelliICLR · University of the Witwatersrand · Simons Foundation · +6
    PDF ↗
  48. 2025
    A Comparative Analysis of LLM Adaptation: SFT, LoRA, and ICL in Data-Scarce ScenariosBernd Bohnet, Rumen Dangovski, Kevin Swersky … Noah FiedelarXiv
    PDF ↗
  49. 2025
    Parameterized Prompt for Incremental Object DetectionZijia An, Boyu Diao, Ruiqi Liu … Yongjun XuarXiv
    PDF ↗
  50. 2025
    Bayesian continual learning and forgetting in neural networksDjohan Bonnet, Kellian Cottart, Tifenn Hirtzlin … Damien QuerliozNature Communications · Centre National de la Recherche Scientifique · Université Paris-Saclay · +4
    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.