unify

Related work

The foundational work on continual learning, 1980 to 2026: methods, theory, benchmarks, surveys, and the neuroscience of memory. Updated weekly; some carry our notes.

15 papers of 8,653Sort Recent · Most cited
Fanman Meng Clear all
  1. 2026
    DesCLIP: Robust Continual Learning via General Attribute Descriptions for VLM-Based Visual RecognitionChiyuan He, Zihuan Qiu, Fanman Meng … Hui LiIEEE Trans. Multimedia · University of Electronic Science and Technology of China
    PDF ↗
  2. 2025
    Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive FusionYukun Chen, Zihuan Qiu, Fanman Meng … Qingbo WuICASSP · University of Electronic Science and Technology of China
    PDF ↗
  3. 2025
    MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model MergingZihuan Qiu, Yidong Xu, Chiyuan He … Hongliang LiNeurIPS · University of Electronic Science and Technology of China · Amazon (Germany) · +1
    PDF ↗
  4. 2025
    Geodesic-Aligned Gradient Projection for Continual Task LearningBenliu Qiu, Heqian Qiu, Haitao Wen … Hongliang LiTIP · University of Electronic Science and Technology of China
  5. 2025
    Distribution-Level Memory Recall for Continual Learning: Preserving Knowledge and Avoiding ConfusionShaoxu Cheng, Kanglei Geng, Chiyuan He … Hongliang LiIEEE Trans. Multimedia · University of Electronic Science and Technology of China
    PDF ↗
  6. 2024
    Dual-Consistency Model Inversion for Non-Exemplar Class Incremental LearningZihuan Qiu, Yi Xu, Fanman Meng … Qingbo WuCVPR · University of Electronic Science and Technology of China · Dalian University of Technology
  7. 2024
    Continual Cross-Domain Image Compression via Entropy Prior Guided Knowledge Distillation and Scalable DecodingChenhao Wu, Qingbo Wu, Rui Ma … Heqian QiuIEEE TCSVT · University of Electronic Science and Technology of China
  8. 2024
    Where to Forget: A New Attention Stability Metric for Continual Learning EvaluationHaojie Wang, Qingbo Wu, Hongliang Li, Fanman MengSpringer CCIS · University of Electronic Science and Technology of China
  9. 2023
    Confusion Mixup Regularized Multimodal Fusion Network for Continual Egocentric Activity RecognitionHanxin Wang, Shuchang Zhou, Qingbo Wu … Heqian QiuICCV
  10. 2023
    Incrementer: Transformer for Class-Incremental Semantic Segmentation with Knowledge Distillation Focusing on Old ClassChao Shang, Hongliang Li, Fanman Meng … Lanxiao WangCVPR · University of Electronic Science and Technology of China
  11. 2023
    CafeBoost: Causal Feature Boost to Eliminate Task-Induced Bias for Class Incremental LearningBenliu Qiu, Hongliang Li, Haitao Wen … Lili PanCVPR · University of Electronic Science and Technology of China
  12. 2023
    GFR: Generic feature representations for class incremental learningZhichuan Wang, Linfeng Xu, Zihuan Qiu … Hongliang LiNeurocomputing · University of Electronic Science and Technology of China
  13. 2023
    Class-Prompting Transformer for Incremental Semantic SegmentationZichen Song, Zhaofeng Shi, Chao Shang … Linfeng XuIEEE Access · University of Electronic Science and Technology of China
  14. 2022
    ISM-Net: Mining incremental semantics for class incremental learningZihuan Qiu, Linfeng Xu, Zhichuan Wang … Hongliang LiNeurocomputing · University of Electronic Science and Technology of China
  15. 2021
    Remember and Reuse: Cross-Task Blind Image Quality Assessment via Relevance-aware Incremental LearningRui Ma, Hanxiao Luo, Qingbo Wu … Linfeng XuACM International Conference on Multimedia · University of Electronic Science and Technology of China
About this index

We keep this list because we read the field and wanted one place to see it. It covers work on continual learning itself, in the core areas of machine learning, and leaves out papers that apply it inside another field, such as medical imaging or fault diagnosis. By default it shows the papers we have a reason to trust: published at a venue like NeurIPS, ICML, ICLR, CVPR or TPAMI, or written by someone who has published there, or cited a few hundred times. The rest are one click away under “All papers”. It is seeded from the community lists kept by ContinualAI and by Xialei Liu, then filled out from OpenAlex, and every week a script looks for new papers on OpenAlex and arXiv. A model reads each candidate and decides whether it belongs; a person reviews the additions before they go live. Authors and affiliations come from OpenAlex, so a recent preprint can lack its institutions for a week or two.

Missing something, or filed under the wrong venue? Write to hello@unify.ai with the arXiv id or DOI.