Continual learning: research map
Learning new tasks or classes over time without forgetting old ones.
1,263 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026), in 4 topics. Within all five venues, its share held steady from 1.3% in 2023–24 to 1.3% in 2025–26 (351 → 576 papers at ICML, NeurIPS, CVPR and AAAI, the venues with data for all four years).
Explore Continual learning in the interactive map
Topics
- Online and replay-based · 582 papers
Theoretical analysis of forgetting, Unified and unsupervised continual frameworks, Gradient projection and plasticity preservation - Class-incremental · 303 papers
Exemplar-efficient class-incremental learning, Class-balanced knowledge retention, Few-shot class-incremental prototypes - Continual fine-tuning of LLMs · 264 papers
Continual pretraining of language models, Mixture-of-experts for multimodal continual tuning, Machine unlearning by selective forgetting - Domain and prompt-based · 114 papers
Domain-incremental learning with memory, Continual test-time adaptation, Prompt-based continual learning
Most cited papers in Continual learning
- iCaRL: Incremental Classifier and Representation Learning (CVPR 2017 · 3,848 citations)
- Large Scale Incremental Learning (CVPR 2019 · 1,269 citations)
- PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning (CVPR 2018 · 1,240 citations)
- Continual Learning Through Synaptic Intelligence (ICML 2017 · 1,007 citations)
- Learning To Prompt for Continual Learning (CVPR 2022 · 762 citations)
- Continual Test-Time Domain Adaptation (CVPR 2022 · 484 citations)
- Experience Replay for Continual Learning (NeurIPS 2019 · 368 citations)
- Rainbow Memory: Continual Learning With a Memory of Diverse Samples (CVPR 2021 · 347 citations)
- Modeling the Background for Incremental Learning in Semantic Segmentation (CVPR 2020 · 344 citations)
- CODA-Prompt: COntinual Decomposed Attention-Based Prompting for Rehearsal-Free Continual Learning (CVPR 2023 · 320 citations)
- Learn From Others and Be Yourself in Heterogeneous Federated Learning (CVPR 2022 · 279 citations)
- PLOP: Learning Without Forgetting for Continual Semantic Segmentation (CVPR 2021 · 265 citations)