Replay-Based Continual Learning

Overview

Replay-based continual learning studies how models can learn from a changing stream of tasks without losing what they learned earlier. Methods store and revisit selected examples, compressed features, prototypes, or generated data, often combining replay with distillation, class balancing, or adaptive scheduling. These approaches are used in settings such as class-incremental vision, language-model fine-tuning, robotics, reinforcement learning, and federated learning. Replay is a strong practical way to balance retention and adaptation, but its benefits depend on memory limits, replay quality and timing, and the cost or privacy risks of retaining past data.

Latest papers

CardsList

138 papers13 papers in the last four weeks, down 28% on the four weeks before. 0.1% of all new papers.

  1. Drift-Conditioned Structural Replay for Continual Cardiac Ultrasound Segmentation

    Nov 15, 2026Zahid Ullah, Jaeyoon Seo, Jihie KimReplay-Based Continual LearningUltrasound Image Segmentation

  2. DLER: Dual-Logit Experience Replay for Online Continual Learning

    Nov 3, 2026Huiwei Lin, Shanshan Feng, Kong Aik LeeOnline Continual LearningReplay-Based Continual Learning

  3. Mitigating Catastrophic Forgetting in Task-Free Federated Continual Forecasting via Two-Tier Replay under Concept Drift

    Oct 31, 2026Khaled Hallak, Oudom KemFederated Continual LearningTask-Free Continual Learning

  4. Class-aware Latent Attention Replay (CLAR): Class Incremental Hazard Diagnosis for Resilient AI in the Manufacturing Industrial Internet

    Oct 29, 2026Avranshu Mahanty, Ran Jin, Yingyan ZengReplay-Based Continual LearningClass-Incremental Learning

  5. CAMR: Compatibility-Aware Memory Replay for Continual Learning in Large Language Models

    Oct 27, 2026Jingpu Yang, Tianhao Li, Fengxian Ji +3Continual LearningContinual Learning for LLMs

  6. ARISE: Authentic Reference-Informed Stability Enhancement for Continual Multimodal Forgery Detection

    Oct 27, 2026Yuchen Zhang, Yaxiong Wang, Yujiao Wu +6Multimodal Deepfake DetectionDeepfake Detection

  7. Entropic Control for Homeostatic Optimization: Pre-empting Catastrophic Forgetting via Dynamic Feedback

    Oct 25, 2026Shangxi Wu, Xiaorong Yan, Xiaojun Meng +2Catastrophic ForgettingContinual Learning for LLMs

  8. Cross-User Adaptation for sEMG Gesture Recognition via Continual Learning

    Oct 25, 2026Aran Ramakrishnan, Shubhi Mishra, Tyler Ham +2EMG-Based Gesture RecognitionContinual Learning

  9. CARES: Coverage-Aware Replay Exemplar Selection for Continual Learning

    Oct 23, 2026Arundhati S. Shanbhag, Brian B. Moser, Federico Raue +2Replay-Based Continual LearningExperience Replay

  10. Why Constrained Updates Still Forget: A Functional-Path Analysis of Continual SFT

    Oct 21, 2026Qingsen Ma, Dianyun Wang, Jiahong Liu +1Supervised Fine-TuningContinual Learning for LLMs

  11. Sparse Autoencoders Can Induce Local Geometry for Mitigating Catastrophic Forgetting

    Oct 15, 2026Kamil Faber, Katarzyna Filus, Łukasz PawelaCatastrophic ForgettingRegularization-Based Continual Learning

  12. Continual Learning for Reliable In-Sequence Molecular Communication

    Oct 14, 2026Siddhant Setia, Junichi Suzuki, Tadashi NakanoReplay-Based Continual LearningIncremental Learning

  13. Overcoming Catastrophic Forgetting: Continual Learning for Radar Waveform Classification

    Oct 13, 2026Mohamed Rabie, Chinthana J. Panagamuwa, Konstantinos G. KyriakopoulosContinual LearningCatastrophic Forgetting

  14. Saliency-Guided Replay for Continual Learning in Deep Spiking Neural Networks

    Oct 13, 2026Francesco Panetta, Federico Di Valerio, Michela ProiettiStorage-Efficient Continual LearningReplay-Based Continual Learning

  15. Self-Preservation in Language Models

    Oct 8, 2026Dongkyu Cho, Rumi Chunara, Ali BehrouzContinual Learning for LLMsReplay-Based Continual Learning

  16. Decentralized collaborative continual learning: A multi-objective minimization-based technique

    Oct 7, 2026Yara Zgheib, Marc Antonini, Roula NassifDecentralized LearningReplay-Based Continual Learning

  17. Catastrophic Forgetting in Sequential Thermal Anti-UAV Detection: The Role of Scale-Conditioned Gradient Imbalance

    Oct 6, 2026Khac Duc Giang Nguyen, Seyed Sahand Mohammadi Ziabari, Ali Mohammed Mansoor AlsahagContinual Object DetectionReplay-Based Continual Learning

  18. What Must Replay Preserve? Separating Correctable Bias from Class Correspondence

    Oct 5, 2026BoRen Deng, Xiangyue Ma, Chenglong Li +1Class-Incremental LearningReplay-Based Continual Learning

  19. VIGIL: Verifier-Informed Gated Improvement Loop for Spreadsheet Question Answering

    Oct 3, 2026Kang Li, Lu He, Sandarsita GuntupalliTable QAContinual Learning for LLM Agents

  20. Replay on Demand: An Emergent Curriculum for Balancing Adaptation and Forgetting in Continued Pretraining

    Sep 30, 2026Lukas Thede, Shengzhuang Chen, Stefan Winzeck +3Continual Learning for LLMsReplay-Based Continual Learning

  21. Experience-Driven Continual Learning of Terrain Traversability for Quadruped Robots

    Sep 30, 2026Luca Bricarello, João Carlos Virgolino Soares, Alberto Sanchez-Delgado +2Continual Robot LearningSafe Robot Navigation

  22. HiTS-CL: A Continual Learning Framework for Long-Horizon Temporal Knowledge Graph Extrapolation

    Sep 29, 2026Yansong Liu, Rui Liu, Yuan Zuo +6Temporal Link PredictionReplay-Based Continual Learning

  23. Reliable Replay through Spatial Coherence in Online Continual Learning

    Sep 27, 2026Haixiang Sun, Jiefu Zhang, Yinghao He +4Continual Learning for LLMsExperience Replay

  24. Beyond Class Marginals: Bounding Rehearsal Gaps without Freezing Class Co-occurrence

    Sep 22, 2026Congren Dai, Nat Roongjirarat, Fei YeClass-Incremental LearningReplay-Based Continual Learning