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 201–250Sort Recent · Most cited
  1. 2026
    GUI-AC: Enhancing Continual Learning in GUI AgentsCan Lin, Tao Feng, Hangjie Yuan … Zhonghong OuarXiv
    PDF ↗
  2. 2026
    Accurate and Resource-Efficient Federated Continual LearningJebacyril Arockiaraj, Dhruv Parikh, Jayashree Adivarahan … Viktor PrasannaarXiv
    PDF ↗
  3. 2026
    Listen, Look, and Learn: Learning Without Forgetting through SAM-AudioAvi Gupta, Nilotpal Sinha, Vishnu Raj … Tammam TilloarXiv
    PDF ↗
  4. 2026
    Preserving Plasticity in Continual Learning via Dynamical IsometryAndries Rosseau, Robert Müller, Ann NowéICML
    PDF ↗
  5. 2026
    Crafting Your Evolving Dreams: Concept-Incremental Versatile CustomizationJiahua Dong, Wenqi Liang, Hongliu Li … Fahad Shahbaz KhanTPAMI · Mohamed bin Zayed University of Artificial Intelligence · University of Trento · +5
    PDF ↗
  6. 2026
    HydraCIL: Decoupled Class-Incremental Learning through Prototype-Guided Multi-Head ClassifiersDaniel Vila-Cruz, Laura Morán‐Fernández, Verónica Bolón-CanedoarXiv
    PDF ↗
  7. 2026PDF ↗
  8. 2026PDF ↗
  9. 2026
    Theoretical Foundations of Continual Learning via Drift-Plus-PenaltyNazreen Shah, Govinda Arya, Bharath B. N., Ranjitha PrasadTMLR
    PDF ↗
  10. 2026PDF ↗
  11. 2026
    Continual Quadruped Robots Coordination via Semantic Skill DiscoveryDaoqing Wang, Yuchen Xiao, Weixuan Huang … Yang YuarXiv
    PDF ↗
  12. 2026PDF ↗
  13. 2026
    Sparse Subspace-to-Expert Sharing for Task-Agnostic Continual LearningFatema Siddika, Md Anwar Hossen, Tanwi Mallick, Ali JannesariarXiv
    PDF ↗
  14. 2026
    Unsupervised Continual Clustering via Forward-Backward Knowledge DistillationM. Sadeghi, Sareh Soleimani, Zihan Wang, N. ArmanfardarXiv
    PDF ↗
  15. 2026
    Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful EnvironmentsParth Asawa, Christopher M. Glaze, Gabriel Orlanski … Joseph E. GonzalezarXiv
    PDF ↗
  16. 2026
    Style-CCL: Content-Preserving Style Transfer via Curriculum Continual LearningShiwen Zhang, Haoyuan Wang, Xianghao Zang … Xuelong LiarXiv
    PDF ↗
  17. 2026
    TailLoR: Protecting Principal Components in Parameter-Efficient Continual LearningMarius Dragoi, Ioana Pintilie, Alexandra Dragomir … Florin BradarXiv
    PDF ↗
  18. 2026PDF ↗
  19. 2026
    CLaaS: Continual learning as a service for sample efficient online learningKion Fallah, Silen Naihin, Barak Widawsky, Qingqing MaoarXiv
    PDF ↗
  20. 2026PDF ↗
  21. 2026
    Rethinking Continual Experience Internalization for Self-Evolving LLM AgentsJingwen Chen, Wenkai Yang, Shengda Fan … Yankai LinarXiv
    PDF ↗
  22. 2026
    Language Models Need Sleep: Learning to Self-Modify and Consolidate MemoriesAli Behrouz, Farnoosh Hashemi, Adel Javanmard, Vahab MirrokniarXiv
    PDF ↗
  23. 2026
    MemoGen: Can Past Experience Improve Future Text-to-Image Generation?Wenshuo Chen, Kuimou Yu, Bowen Tian … Yutao YuearXiv
    PDF ↗
  24. 2026
    Re-Evaluating Continual Learning with Few-Shot AdaptationAmogh Inamdar, Matthew So, Vici Milenia, Richard ZemelarXiv
    PDF ↗
  25. 2026
    PHASER: Phase-Aware and Semantic Experience Replay for Vision-Language-Action ModelsZiyang Chen (3956366), Shaoguang Wang, Weiyu Guo … Yandong GuoarXiv
    PDF ↗
  26. 2026PDF ↗
  27. 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 ↗
  28. 2026PDF ↗
  29. 2026
    AgentCL: Toward Rigorous Evaluation of Continual Learning in Language AgentsYiheng Shu, Bernal Jiménez Gutiérrez, Saisri Padmaja Jonnalagedda … Yu SuarXiv
    PDF ↗
  30. 2026
    Training Prompt Matters: State-Adaptive Optimization for Robust Fine-TuningWenhang Shi, Yiren Chen, Shuqing Bian … Xiaoyong DuarXiv
    PDF ↗
  31. 2026PDF ↗
  32. 2026
    CRAM: Centroid-Routing and Adaptive MoE for Multimodal Continual Instruction TuningJun-Tao Tang, Zhen-Hao Xie, Yu-Cheng Shi, Da-Wei ZhouarXiv
    PDF ↗
  33. 2026PDF ↗
  34. 2026PDF ↗
  35. 2026
    LAPS: Improving Incremental LiDAR Mapping Using Active Pooling and Sampling for Neural Distance FieldsDongjae Lee, Wooseong Yang, Yifu Tao … Ayoung KimRA-L · Seoul National University · University of Oxford
    PDF ↗
  36. 2026PDF ↗
  37. 2026PDF ↗
  38. 2026PDF ↗
  39. 2026
    Continual test-time adaptation for object detection with adaptive monitoring and randomized restorationShilei Cao, Juepeng Zheng, Yan Liu … Haohuan FuExpert Systems with Applications · Sun Yat-sen University · National Supercomputing Center in Shenzhen · +4
    PDF ↗
  40. 2026PDF ↗
  41. 2026
    Beyond Classification: Dynamic Adapter Routing for Continual Multimodal RetrievalAlicja Dobrzeniecka, Filip Szatkowski, Sebastian Cygert … Bartlomiej TwardowskiarXiv
    PDF ↗
  42. 2026
    Canonicalized Stable-List Replay for Private Federated Continual Learning over Language-Model EmbeddingsIbne Farabi Shihab, Abu Sa-Adat Mohamed Moon-Im Al Ahsan, Anuj SharmaarXiv
    PDF ↗
  43. 2026
    Don't Fool Me Twice: Adapting to Adversity in the Wild with Experience-Driven ReasoningNavin Sriram Ravie, Andrew Jong, Krrish Jain … Sebastian SchererarXiv
    PDF ↗
  44. 2026PDF ↗
  45. 2026PDF ↗
  46. 2026
    Task-Focused Memorization for Multimodal AgentsTao Zou, Yichen He, Tian Qiu … Hang LiarXiv
    PDF ↗
  47. 2026
    On-Policy Replay for Continual Supervised Fine-TuningYan Chen, Taojie Zhu, Meng Zhang … Yizhi WangarXiv
    PDF ↗
  48. 2026
    Overcoming Forgetting in LLM Fine-Tuning with Evolution StrategiesKajetan Schweighofer, Conor F. Hayes, Roberto Dailey … Xin QiuarXiv
    PDF ↗
  49. 2026
    Active Continual Learning with Metaplastic Binary Bayesian Neural NetworksKellian Cottart, Théo Ballet, Djohan Bonnet, Damien QuerliozICML
    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.