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.

6,984 papers · showing 601–650Sort Recent · Most cited
  1. 2026PDF ↗
  2. 2026
    Dynamic expansion orthogonal network for class-incremental learningMingda Dong, Zhizhong Zhang, Xin Tan … Yuan XieKnowledge-Based Systems · East China Normal University · Shandong Provincial QianFoShan Hospital · +1
  3. 2026PDF ↗
  4. 2026
    Corrective Distillation: Mitigating Catastrophic Forgetting in LLM Fine-Tuning via External Correction of Self-Generated ErrorsJianchun Jiang, Yingfei Qu, Hui LiInternational Conference on Generative Artificial Intelli… · Chongqing Technology and Business University
  5. 2026
    Dual-Stage Invariant Continual Learning under Extreme Visual SparsityRangya Zhang, Jiaping Xiao, Lu Bai … Mir FeroskhanarXiv
    PDF ↗
  6. 2026
    HAD: Heterogeneity-Aware Distillation for Lifelong Heterogeneous LearningXuerui Zhang, Xuehao Wang, Zhan Zhuang … Yu ZhangCVPR
    PDF ↗
  7. 2026
    Recent Advances of Multimodal Continual Learning: A Comprehensive SurveyDianzhi Yu, Xinni Zhang, Yankai Chen … Irwin KingTNNLS · Chinese University of Hong Kong · Tsinghua University · +1
    PDF ↗
  8. 2023
    A Parameter-free Adaptive Resonance Theory-based Topological Clustering Algorithm Capable of Continual LearningNaoki Masuyama, Takanori Takebayashi, Yusuke Nojima … Stefan WermterNeural Computing and Applications · Osaka Prefecture University · University of Malaya · +2
    PDF ↗
  9. 2026
    Evidence of an Emergent "Self" in Continual Robot LearningAdidev Jhunjhunwala, Judah Goldfeder, Hod LipsonarXiv
    PDF ↗
  10. 2026
    Few-shot class-incremental learning based on prompt guidance and multimodal fusionHaoming Fang, Haonan Cai, Keming Mao … Xinlu XiaoKnowledge-Based Systems · Northeastern University · China Mobile (China)
  11. 2026PDF ↗
  12. 2026
    Balanced Online Class-Incremental Learning via Dual ClassifiersShunjie Wen, Thomas Heinis, Dong-Wan ChoiACM/SIGAPP Symposium on Applied Computing · Inha University · Imperial College London
    PDF ↗
  13. 2026PDF ↗
  14. 2026
    Multi-Scale Adaptive Convolutional Graph for Multi-Stream Concept DriftMing Zhou, Jie Lu, Guangquan ZhangTKDE · University of Technology Sydney
  15. 2026PDF ↗
  16. 2026
    Pruned Adaptation Modules: A Simple yet Strong Baseline for Continual Foundation ModelsElif Ceren Gok Yildirim, Murat Onur Yildirim, Joaquin VanschorenarXiv
    PDF ↗
  17. 2026
    Reframing Long-Tailed Learning via Loss Landscape GeometryShenghan Chen, Yiming Liu, Yanzhen Wang … Xiankai LuarXiv
    PDF ↗
  18. 2026PDF ↗
  19. 2026
    G-Scaler: Graph few-shot class-incremental learning via structural coupling and elegant shift rectificationBin Wang, Boxiang Tao, Hongbo Dou … Lin LuoNeurocomputing · China University of Petroleum, East China
  20. 2026
    Memento-Skills: Let Agents Design AgentsHuichi Zhou, Siyuan Guo, Anjie Liu … Jun WangarXiv
    PDF ↗
  21. 2026PDF ↗
  22. 2026PDF ↗
  23. 2026PDF ↗
  24. 2026
    Learning task-shared and specific knowledge via mixture-of-experts in generative model for continual learningWeinan Zhao, Yanling Ji, Yan Li … Dingwen ZhangPattern Recognition · Northwestern Polytechnical University · Xidian University · +1
  25. 2026PDF ↗
  26. 2026
    Structural Abstraction as an Inductive Bias for Non-Stationary Language Model TrainingElnaz Rahmati, Nona Ghazizadeh, Zhivar Sourati … Morteza DehghaniarXiv
    PDF ↗
  27. 2026
    Training constrains neural routes to knowledge assemblyQiyao Wang, Compton French, Pooja Bansiya … Stephanie NellibioRxiv · Occidental College
    PDF ↗
  28. 2026
    MMKU-Bench: A Multimodal Update Benchmark for Diverse Visual KnowledgeBaochen Fu, Yuntao Du, Cheng Chang … Yi WanarXiv
    PDF ↗
  29. 2026
    CATFormer: When Continual Learning Meets Spiking Transformers With Dynamic ThresholdsVaishnavi Nagabhushana, Kartikay Agrawal, Ayon BorthakurarXiv
    PDF ↗
  30. 2026
    GAIN: Global-Atomic INteraction Graph for Few-Shot Class-Incremental LearningFan Lyu, Linglan Zhao, Changli Liu … Liang WangIEEE TCSVT · Chinese Academy of Sciences · Institute of Automation · +6
  31. 2026
    SCAN: Sparse Circuit Anchor Interpretable Neuron for Lifelong Knowledge EditingYuhuan Liu, Haitian Zhong, Xinyuan Xia … Liang WangarXiv
    PDF ↗
  32. 2026PDF ↗
  33. 2026
    Fine-tuning MLLMs Without Forgetting Is Easier Than You ThinkHe Li, Yuhui Zhang, Xiaohan Wang … Serena Yeung-LevyarXiv
    PDF ↗
  34. 2026
    Unlearning-based sliding window for continual learning under concept driftMichal Wozniak, Marek Klonowski, Maciej Maczyński, Bartosz KrawczykarXiv
    PDF ↗
  35. 2026
    Put the Space of LoRA Initialization to the Extreme to Preserve Pre-trained KnowledgePengwei Tang, Xiaolin Hu, Yong Liu … Debing ZhangAAAI · Beijing Academy of Artificial Intelligence · Ministry of Education · +3
    PDF ↗
  36. 2026
    Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time AdaptationRongyu Zhang, Aosong Cheng, Y. Luo … Yuan DuAAAI · Hong Kong Polytechnic University · Peking University · +3
    PDF ↗
  37. 2026
    BOFA: Bridge-Layer Orthogonal Low-Rank Fusion for CLIP-Based Class-Incremental LearningLan Li, Tao Hu, Da-Wei Zhou … De-Chuan ZhanAAAI · Nanjing University
    PDF ↗
  38. 2026
    MoETTA: Test-Time Adaptation Under Mixed Distribution Shifts with MoE-LayerNormXiao Fan, Jingyan Jiang, Zhaoru Chen … Zhi WangAAAI · University Town of Shenzhen · Shenzhen Technology University · +1
    PDF ↗
  39. 2026
    KSS-MoE: Knowledge Space Synergy Framework in Mixture of Experts for Continual Visual Instruction TuningLingyun Song, Ziyao Chen, Kang Pan … Xuequn ShangAAAI · Northwestern Polytechnical University · San Francisco Bay University · +1
    PDF ↗
  40. 2026
    Continual Out-of-Distribution Detection with Analytic Neural CollapseSaleh Momeni, Changnan Xiao, Bing Jie Darius LiuAAAI · University of Illinois Chicago
  41. 2026
    DeLo: Dual Decomposed Low-Rank Experts Collaboration for Continual Missing Modality LearningXiwei Liu, Yulong Li, Feilong Tang, Imran RazzakAAAI · Mohamed bin Zayed University of Artificial Intelligence
    PDF ↗
  42. 2026PDF ↗
  43. 2026PDF ↗
  44. 2026
    Grow-on-Demand: Sparse and Adaptive Expert Expansion for Continual Instruction TuningYing Zhang, Xingyue Guo, Yu Zhao … Xiaojie YuanAAAI · Nankai University · Tiangong University
    PDF ↗
  45. 2026
    Learning Adaptive and Expandable Mixture Model for Continual LearningFei Ye, yongcheng zhong, Qihe Liu … Shijie ZhouAAAI · University of Electronic Science and Technology of China · University of York
    PDF ↗
  46. 2026
    Online Cross-Modal Hashing with Expanding Label SpaceWentao Fan, Chao Zhang, Chunlin Chen, Huaxiong LiAAAI · Nanjing University
  47. 2026
    PAL: Prompting Analytic Learning with Missing Modality for Multi-Modal Class-Incremental LearningXianghu Yue, Yiming Chen, Xueyi Zhang … Haizhou LiPattern Recognition · Tianjin University · National University of Singapore · +4
    PDF ↗
  48. 2026
    Rep Deep & Machine Learning: Exemplar-Free Continual Video Action Recognition via Slow-Fast Collaborative LearningXueyi Zhang, Jianhua Zhang, Zheng Li … Huiping ZhuangAAAI · Chinese University of Hong Kong, Shenzhen · University of Chinese Academy of Sciences · +4
    PDF ↗
  49. 2026
    Zero-Forgetting CISS via Dual-Phase Cognitive CascadesYuquan Lu, Yifu Guo, Zishan Xu … Ruixuan WangarXiv
    PDF ↗
  50. 2026
    Adversarial Perturbation Shield: Preventing Concept Bleed-through in Continual Learning of Personalized Generative ModelsZiwen Lan, Keisuke Maeda, Takahiro Ogawa, Miki HaseyamaAAAI · Hokkaido University
    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.