Replay-Based Continual Learning

Ask about this topic

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

134 papers20 papers in the last four weeks, up 82% on the four weeks before. 0.1% of all new papers.

  1. Enhancing Continual Learning for Software Vulnerability Prediction: Addressing Catastrophic Forgetting via Hybrid-Confidence-Aware Selective Replay for Temporal LLM Fine-Tuning

    Feb 27, 2026Xuhui Dou, Hayretdin Bahsi, Alejandro Guerra-ManzanaresSoftware Vulnerability DetectionContinual Learning for LLMs

    School of Computer Science, University of Nottingham, Nottingham, United Kingdom · School of Informatics and Computing, Northern Arizona University, Flagstaff, United States of America · School of Computer Science, University of Nottingham, Ningbo, China

  2. Footprint-Guided Exemplar-Free Continual Histopathology Report Generation

    Feb 27, 2026Pratibha Kumari, Daniel Reisenbüchler, Afshin Bozorgpour +3Medical Report GenerationContinual Learning for VLMs

    Faculty of Informatics and Data Science, University of Regensburg, Germany · Indian Institute of Information Technology Bhopal, India

  3. Efficient Continual Learning in Language Models via Thalamically Routed Cortical Columns

    Feb 25, 2026Afshin KhadangiContinual Learning for LLMsDecoder-Only Language Models

    SnT, University of Luxembourg

  4. Understanding the Role of Rehearsal Scale in Continual Learning under Varying Model Capacities

    Feb 24, 2026JinLi He, Liang Bai, Xian YangContinual LearningReplay-Based Continual Learning

    Institute of Intelligent Information Processing, Shanxi University, Taiyuan, 030006, China · Alliance Manchester Business School, The University of Manchester, Manchester, M13 9PL, UK

  5. Latent Replay Detection: Memory-Efficient Continual Object Detection on Microcontrollers via Task-Adaptive Compression

    Feb 24, 2026Bibin WilsonContinual Object DetectionObject Detection

    Independent Researcher

  6. AHC: Meta-Learned Adaptive Compression for Continual Object Detection on Memory-Constrained Microcontrollers

    Feb 24, 2026Bibin WilsonContinual Object DetectionObject Detection

    Independent Researcher

  7. Trust Region Continual Learning as an Implicit Meta-Learner

    Feb 2, 2026Zekun Wang, Anant Gupta, Christopher J. MacLellanReplay-Based Continual LearningTask-Incremental Learning

    Georgia Institute of Technology

  8. Knowledge-Aware Evolution for Task-Free Streaming Federated Continual Learning with Arbitrary Class Overlap

    Jan 27, 2026Sixing Tan, Xianmin LiuContinual LearningFederated Continual Learning

    Faculty of Computing Harbin Institute of Technology

  9. When Less is More: 8-bit Quantization Improves Continual Learning in Large Language Models

    Dec 22, 2025Michael S. Zhang, Rishi A. Ruia, Arnav Kewalram +3LLM QuantizationContinual Learning for LLMs

    Algoverse

  10. ProDER: A Continual Learning Approach for Fault Classification and Localization in Evolving Smart Grids

    Nov 7, 2025Emad Efatinasab, Nahal Azadi, Davide Dalle Pezze +3Replay-Based Continual LearningPrototype-Based Classification

    Department of Information Engineering, University of Padova. · School of Computing, Newcastle University.

  11. Taming Modality Entanglement in Continual Audio-Visual Segmentation

    Oct 20, 2025Yuyang Hong, Qi Yang, Tao Zhang +5Audio-Visual UnderstandingReplay-Based Continual Learning

    School of Artificial Intelligence, UCAS · 2MAIS, Institute of Automation · School of Intelligent Science and Technology, University of Science and Technolog Beijing

  12. Beyond Discrete Samples: High Information Density Replay for Efficient Lifelong Person Re-Identification

    Aug 3, 2025Mingyu Wang, Haojie Liu, Zhiyong Li +3Replay-Based Continual LearningDataset Condensation

    College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China

  13. HERO: Preserving Structure and Semantics in Heterogeneous Continual Graph Learning

    May 23, 2025Guiquan Sun, Xikun Zhang, Jingchao Ni +1Heterogeneous GNNsReplay-Based Continual Learning

    School of Computing, University of Connecticut · RMIT University, Melbourne · Department of Computer Science, University of Houston

  14. Exploiting Stability-Plasticity Asymmetry in Pretrained Detectors for Incremental Object Detection

    Apr 14, 2025Songze Li, Qixing Xu, Tonghua Su +3Class-Incremental LearningDetection Transformer

    Harbin Institute of Technology, Harbin, China · Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China · Chongqing Research Institute of HIT, Chongqing, China +2