2 papers
cs.LG2026
AG-TAL: Anatomically-Guided Topology-Aware Loss for Multiclass Segmentation of the Circle of Willis Using Large-Scale Multi-Center Datasets
Jialu Liu, Yue Cui, Shan Yu
Accurate multiclass segmentation of the Circle of Willis (CoW) is essential for neurovascular disease management but remains challenging due to complex vascular topology and variab…
cs.LG2026
Towards Unified Multi-task EEG Analysis with Low-Rank Adaptation
Sicheng Dai, Kai Chen, Hongwang Xiao +2
Recent self-supervised pre-training methods for electroencephalogram (EEG) have shown promising results. However, the pre-trained models typically require full fine-tuning on each…