On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models
Paper • 2603.27481 • Published • 35
Zishan Qin
taylorqin
AI & ML interests
None yet
Recent Activity
liked a model 3 months ago
facebook/dinov3-vitl16-pretrain-lvd1689m liked a dataset 8 months ago
ShapeNet/shapenetcore-glbOrganizations
None yet