Overview

Online continual learning studies how models can learn from data as it arrives, often in a single pass and without known task boundaries, while retaining useful information from the past. Common approaches use replay buffers or structured memories, constrain updates with regularization or parameter-efficient adapters, expand model capacity, or detect distribution shifts to trigger targeted updates. Researchers evaluate these methods on streaming vision and language tasks, time-series drift, robotics, and resource-constrained devices, measuring accuracy, forgetting, transfer, memory, and compute. A central challenge is balancing adaptation to new or recurring patterns against retention, while ensuring results hold under realistic streams and do not depend on hidden assumptions such as task labels or pretrained features.

Latest papers

CardsList

116 papers12 papers in the last four weeks, down 43% on the four weeks before. 0.1% of all new papers.

  1. Hypnos: A Dual-Phase End-to-End Platform for Scalable Continual Learning at the Edge

    Nov 18, 2026Guilherme Guedes, Marco Apolinario Lainez, Charlotte FrenkelContinual LearningOnline Continual Learning

  2. GaussLearner: 3D Gaussian Primitives as Self-Regulating Continual Learners

    Nov 18, 2026Gaoxiang Linghu, Haonan Zhou, Xuanhe Liu +43D Gaussian Splatting3D Reconstruction

  3. DuoCL: Dual-Path Online Continual Learning

    Nov 17, 2026Jebacyril Arockiaraj, Dhruv Parikh, Rajgopal Kannan +1Continual LearningOnline Continual Learning

  4. Open-world Reconstruction-based Classifier with Concept Drift Adaptation

    Nov 6, 2026Joanna KomorniczakConcept DriftOpen-Set Recognition

  5. Permanent and Transient Representations for Continual Reinforcement Learning

    Nov 5, 2026Nishanth Anand, Doina PrecupComplementary Learning SystemsContinual Learning

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

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

  7. Online Label-Free Gradient Matching for Continual Language Model Training

    Nov 2, 2026Sajjad Pakdamansavoji, Mohammad Reza Rezaei, Ilija Subasic +3Continual Learning for LLMsDataset Distillation

  8. Hippocampal consolidation without replay in fully fine-tuned networks

    Nov 1, 2026Keuntae Kim, Yong Suk ChoiCatastrophic ForgettingClass-Incremental Learning

  9. AutoHebb: Self-Modifying Neural Networks that Zero-Shot Infer and Continually Learn

    Oct 29, 2026Daniel Levine, David van Dijk, Kenneth KayOnline Continual LearningZero-Shot Learning

  10. 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

  11. Recall or Relearn? A Mixture of In-Context Experts for Recurring Concept Drift

    Oct 27, 2026Zhangkai Wu, Xu Zhang, Zhihong Cui +2Concept DriftOnline Continual Learning

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

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

  13. Online Continual Learning in Edge-Cloud Applications

    Oct 23, 2026Charalampos Davalas, Dimitrios Michail, Christos Diou +2Online Continual LearningEdge ML

  14. Time to Fake It: Continual Machine Learning Intensifies Unfairness in Deepfake Detection

    Oct 15, 2026Kajaree Das, Oliver Böse, Subarnaduti Paul +2Algorithmic FairnessDeepfake Detection

  15. Optimal Explicit and Implicit Regularization Strengths in High-Dimensional Continual Linear Regression

    Oct 14, 2026Gilad Karpel, Daniel SoudryHigh-Dimensional Linear RegressionRegularization-Based Continual Learning

  16. Formalizing Forgetting: Theory of Forgetting for Online Continual Learning

    Oct 10, 2026Renjie Cao, Yifei Cheng, Li ShenOnline Continual LearningCatastrophic Forgetting

  17. Recurrent Harness for Agentic Continual Learning

    Oct 8, 2026Yuxin Xiao, Zhiyun Lu, Jianyu Wang +4Continual Learning for LLM AgentsAgent Harness Optimization

  18. Benchmarking Label-Revealed Online Updates for EEG BCI Decoding

    Oct 5, 2026Bogdan Kozyrskiy, Artem Grachev, Abraham I. Camelo GuerreroBrain-Computer InterfacesEEG Decoding

  19. LiLib: Lifelong Air-to-Ground Path-Loss Prediction on UAVs via a Drift-Triggered Model Library

    Oct 5, 2026Minh TranConcept DriftWireless Communications

  20. Task Vector Descent: Learning from Non-IID Batches

    Oct 4, 2026Anton Baumann, Jonas Hübotter, Zeynep Akata +1Continual Learning for LLMsTask Arithmetic

  21. AIBL: Augmented Instance-Based Learning with Structured Memory and Neural Embeddings

    Oct 2, 2026Radha Poovendran, Andrea Stocco, Linda BushnellOnline Continual LearningMemory-Augmented Neural Networks

  22. AIGS: Adaptive Incremental Gating System for Online Representation Learning in Non-Stationary Data Streams

    Oct 2, 2026SiRui He, Kai Liang Lew, Chui Zi Ong +1Time Series Representation LearningRepresentation Learning

  23. Continual Learning for 6-DoF Grasp Synthesis via Experience and Demonstrations

    Oct 1, 2026Giulio Schiavi, Andrei Cramariuc, Michael Pantic +1Robotic GraspingContinual Robot Learning

  24. A Dynamical Theory of LoRA in Continual Learning

    Sep 30, 2026Théo Marchetta, Filippo Alessandroni, Alessandro Breccia +2Continual LearningLow-Rank Adaptation

  25. 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

  26. Online Versatile Incremental Learning: Towards Class and Domain-Agnostic Adaptation at Any Time

    Sep 29, 2026Jae-Ho Lee, Min-Yeong Park, Jun-Yeong Moon +2Class-Incremental LearningDomain-Incremental Learning