Yung-Hsuan Lai

Latest

• Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers
• Select and Distill: Selective Dual-Teacher Knowledge Transfer for Continual Learning on Vision-Language Models
• RAPPER: Reinforced Rationale-Prompted Paradigm for Natural Language Explanation in Visual Question Answering
• Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser