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.

16 papers of 8,653Sort Recent · Most cited
Heqian Qiu University of Electronic Science and Technology of China Clear all
  1. 2026
    Spatial-Temporal Side Adaptation with Difference-based Frame Selector for video class-incremental learningYu Dai, Heqian Qiu, Lanxiao Wang … Hui LiDisplays · University of Electronic Science and Technology of China
  2. 2026
    Parameter Merging with Gradient-Guided Supermasks in Online Continual LearningBenliu Qiu, Heqian Qiu, Lanxiao Wang … Hongliang LiAAAI · University of Electronic Science and Technology of China
  3. 2025
    D3Net: Dual-Path Decoupling-Distillation for Adaptive Fusion in Continual Egocentric LearningChenghao Qi, Heqian Qiu, Zhaofeng Shi … Hongliang LiIEEE International Workshop on Multimedia Signal Processi… · University of Electronic Science and Technology of China
  4. 2025
    DBAB: A Dual-Branch Adaptive Balance Framework with Optimized Plasticity Branch for Class-Incremental LearningXinyu Chen, Heqian Qiu, Chenghao Qi … Hongliang LiIEEE International Workshop on Multimedia Signal Processi… · University of Electronic Science and Technology of China
  5. 2025
    OrthCal: Synergizing Orthogonal Contrastive Learning and Prototype Calibration for Few-Shot Class-Incremental LearningRuisong Dai, Hanwen Zhang, Xinyu Chen … Hongliang LiIEEE International Workshop on Multimedia Signal Processi… · University of Electronic Science and Technology of China
  6. 2025
    Adaptively forget with crossmodal and textual distillation for class-incremental video captioningHuiyu Xiong, Lanxiao Wang, Heqian Qiu … Hongliang LiNeurocomputing · University of Electronic Science and Technology of China
  7. 2025
    Geodesic-Aligned Gradient Projection for Continual Task LearningBenliu Qiu, Heqian Qiu, Haitao Wen … Hongliang LiTIP · University of Electronic Science and Technology of China
  8. 2024
    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 ↗
  9. 2025
    Class Incremental Learning With Less Forgetting Direction and Equilibrium PointHaitao Wen, Heqian Qiu, Lanxiao Wang … Hongliang LiIEEE TCSVT · University of Electronic Science and Technology of China
  10. 2024
    Video Class-Incremental Learning With Clip Based TransformerShuyun Lu, Jian Jiao, Lanxiao Wang … Hongliang LiICIP · University of Electronic Science and Technology of China
  11. 2024
    Must Unsupervised Continual Learning Relies on Previous Information?Haoyang Cheng, Haitao Wen, Heqian Qiu … Hongliang LiCVPR · University of Electronic Science and Technology of China
  12. 2024
    Class Incremental Learning with Multi-Teacher DistillationHaitao Wen, Lili Pan, Yu Dai … Hongliang LiCVPR · University of Electronic Science and Technology of China
  13. 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
  14. 2023
    Contrastive Continuity on Augmentation Stability Rehearsal for Continual Self-Supervised LearningHaoyang Cheng, Haitao Wen, Xiaoliang Zhang … Hongliang LiICCV · University of Electronic Science and Technology of China
  15. 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
  16. 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
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. 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.