Overview

Incremental learning studies how a model can learn from data that arrives over time—such as new classes, changing domains, or streaming examples—without losing what it learned before. Common approaches replay stored examples, regularize or distill the model to preserve earlier behavior, or isolate and expand parts of the model with adapters, experts, or new parameters. Methods are evaluated in settings such as class-, domain-, and task-incremental learning, using benchmarks including CIFAR-100, ImageNet variants, and language-task sequences; newer work also considers pretrained multimodal models, long-tailed data, and task-free streams. The central tension is stability versus plasticity: preserving old knowledge can hinder learning new information, while memory, model growth, task-order effects, and realistic evaluation remain open challenges.

Latest papers

CardsList

151 papers7 papers in the last four weeks, down 70% on the four weeks before. 0.1% of all new papers.

  1. [CLS] and [EOS] Tokens are not Enough for CLIP-based Class-Incremental Learning

    Nov 16, 2026Hao Sun, Tao Hu, Shixiong Kai +4Incremental LearningContinual Learning for VLMs

  2. STABLE: A Continual Learning Optimizer with Adaptive Drift Control

    Nov 7, 2026Xiaoyan Li, Lanpei Li, Massimo Coppola +2Continual LearningIncremental Learning

  3. ROSE: Risk-Aware Orthogonal Subspace Navigation for Lifelong Knowledge Editing in Multimodal Large Language Models

    Nov 6, 2026Lingyun Song, Ziyao Chen, Kang Pan +5Subspace-Based Continual LearningKnowledge Editing

  4. What Is the Influence of Task Order in Continual Learning? An Empirical Study and Order-Aware Evaluation for Motion Forecasting

    Nov 3, 2026Zirui Li, Yunlong Lin, Haohan Yang +2ForecastingContinual Learning

  5. CoPE-CGL: Community-aware Prototype Extraction for Replay-Free Continual Graph Learning

    Oct 26, 2026Bo-Young Lim, Seokhwan Kim, Kisung Lee +1Incremental Learning

  6. LSA-PAST: Layer-Specific Adaptation and Prototype Transport for Compositional Incremental Learning

    Oct 19, 2026Kyle Stein, Andrew Arash Mahyari, Guillermo Francia +2Incremental LearningClass-Incremental Learning

  7. Learning without Overwriting: Structural Knowledge Fusion for Continual Learning

    Oct 18, 2026Kanishk Bakshi, Amitansu Pattanaik, Kathiravan SrinivasanClass-Incremental LearningIncremental Learning

  8. Co2In: a Bi-level Memory Incremental Learning Framework with Knowledge Encoding, Consolidation, and Integration

    Oct 15, 2026Wenju Sun, Qingyong Li, Boyang Li +4Task-Incremental LearningIncremental Learning

  9. Functional Subnetwork Localization for Efficient Continual Learning in Large Language Models

    Oct 15, 2026Shuoran Jiang, Wentao Zhu, Yang Xiang +8Continual Learning for LLMsIncremental Learning

  10. Continual Learning for Reliable In-Sequence Molecular Communication

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

  11. SPARS: A Stability-Plasticity-Aware Region Selection Framework for Continual Learning

    Oct 14, 2026Teif Aldaajani, Huda Hakami, Maha A. ThafarRegularization-Based Continual LearningParameter Isolation

  12. 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

  13. When Skills Remain But Access Fails: Factorized Skill Memory for Continual Skill Internalization

    Oct 11, 2026Haomiao Qiu, Yining Tang, Hongyi Wan +3Continual Learning for LLM AgentsAgent Skill Learning

  14. CoDe-LoRA: Mitigating the Orthogonality Dilemma in Continual Learning of LLMs via Knowledge Consolidation and Decoupling

    Oct 6, 2026Maoqi Liu, Quan Fang, Yufei HeContinual Learning for LLMsLow-Rank Adaptation

  15. HiER-BLS: A Hierarchy-Guided and Error-Correcting Robust Incremental Broad Learning System

    Oct 5, 2026Gongli Zhang, C. L. Philip Chen, Zhulin LiuHierarchical Representation LearningNeural Network Robustness

  16. MAGIC: Topology-Aware Analytic Graph Few-Shot Class-Incremental Learning

    Oct 4, 2026Junlin Chen, Yuhan Wang, Xuefei Wang +3Class-Incremental LearningContinual Learning

  17. One-Step Curvature Probes Miss the Fitting Operator: Retained Capacity and Terminal Null-Space Correction for Continual Learning

    Oct 2, 2026Abu Sa-Adat Mohamed Moon-Im Al Ahsan, Ibne Farabi Shihab, Md Najmus SwaqeebContinual LearningIncremental Learning

  18. Width Expansion as a Method for Class Incremental Learning

    Sep 29, 2026A. L. S. Conde, Y. Elkhatib, C. M. RanieriClass-Incremental LearningDynamic Neural Networks

  19. Learning as Deepfakes Evolve: RF-Prompt for Continual Audio Deepfake Detection

    Sep 29, 2026Yuankun Xie, Xiaoxuan Guo, Xiaopeng Wang +3Audio Deepfake DetectionPrompt Learning

  20. Re:Cognize -- A Framework For Open-Set Comic Character Re-Identification

    Sep 27, 2026Aaditya Baranwal, Madhav Kataria, Yogesh S Rawat +1Self-TrainingOpen-Set Recognition

  21. Continual Learning via Self-Probe Gradients

    Sep 26, 2026Dongkyu Cho, Rumi Chunara, Sungmin ChaContinual Learning for LLMsCatastrophic Forgetting

  22. HCPN-GCN: Scaling Hierarchical Prototype Networks with Cone Geometry for Continual Graph Learning

    Sep 25, 2026Sammuel R. Silva, Vander L. S. Freitas, Gladston Moreira +2Incremental LearningHierarchical Representation Learning

  23. A Lightweight Plastic-Memory Framework for Graph Few-Shot Class-Incremental Learning

    Sep 22, 2026Zihan Mei, Zhili Qin, Tongze Zhang +3Class-Incremental LearningFew-Shot Learning

  24. Lightweight Ranking Heads: Accelerating Multi-Task Experimentation in Production Recommender Systems

    Sep 21, 2026Sanjay Surendranath Girija, Aniruddh Nath, Li Wei +6Learning to RankMulti-Task Learning

  25. Muon Can Outperform Dedicated Continual Learning Methods

    Sep 21, 2026Sebastian George Sincari, Bogdan Alexandru Gheorghe, Antonio BarbalauContinual LearningMuon Optimizer