Tung Lam Tran

Boosting Multiple Views for pretrained-based Continual Learning

Enhancing Domain Adaptation through Prompt Gradient Alignment

Conditional Support Alignment for Domain Adaptation with Label Shift

Improving Multi-task Learning via Seeking Task-based Flat Regions

Improving Prompt-based Continual Learning with Key-Query Orthogonal Projection and Prototype-based One-Versus-All