activity
20202026
most citedDual Prototypes for Adaptive Pre-Trained Model in Class-Incremental Learning

1 citations · 1 across the 28 of their papers we have counts for

collaborators

29 papers

cs.LG2026

Task-Anchored Representation Shaping for Pre-Trained Model-Based Continual Learning

Zhiming Xu, Huiyu Yi, Zhen-Hao Xie +4

Pre-trained models (PTMs) provide a strong foundation for continual learning by offering stable representations that facilitate lightweight adaptation to new tasks. However, adapti…

cs.AI2026

Beyond Routing Saturation: A Long-Horizon Class-Incremental Perspective on Expert Routing in Multimodal Continual Instruction Tuning

Huiyu Yi, Yongqi Xu, Bogang Zhang +5

Multimodal Continual Instruction Tuning (MCIT) enables multimodal large language models to acquire new tasks sequentially while retaining previously learned capabilities. Many rece…

cs.CV2026

Redirecting the Flow: Image Customization through Attention Distribution Shift

Jie Li, Suorong Yang, Jian Zhao +1

Subject-driven image customization aims to generate images that not only follow textual instructions but also preserve the identity of a given reference subject. Existing approache…

cs.LG2026

Directional Linear Separability of Neural Representations: Geometry and Transformations

Yi Wei, Xuan Qi, Furao Shen +1

Neural networks build representations through affine maps and nonlinear activations. Injective affine maps preserve linear separability, raising the problem of how they prepare dat…

cs.LG2026

Beyond What to Select: A Plug-and-play Oscillatory Data-Volume Scheduling for Efficient Model Training

Suorong Yang, Hanqi Zhu, Hai Gan +4

Data selection accelerates training by identifying representative training data while preserving model performance. However, existing methods mainly focus on designing sample-impor…

cs.CV2026

Beyond Point-wise Neural Collapse: A Topology-Aware Hierarchical Classifier for Class-Incremental Learning

Huiyu Yi, Zhiming Xu, Dunwei Tu +3

The Nearest Class Mean (NCM) classifier is widely favored in Class-Incremental Learning (CIL) for its superior resistance to catastrophic forgetting compared to Fully Connected lay…