Yun Sing Koh

Detect, Decide, Unlearn: A Transfer-Aware Framework for Continual Learning

Timed Dynamic Expansion for Continual Learning

Unlearning during Training: Domain-Specific Gradient Ascent for Domain Generalization

Multiple Images Distract Large Multimodal Models via Attention Fragmentation

Model-agnostic Adversarial Attack and Defense for Vision-Language-Action Models

SATCH: Specialized Assistant Teacher Distillation to Reduce Catastrophic Forgetting

Balancing Domain-Invariant and Domain-Specific Knowledge for Domain Generalization with Online Knowledge Distillation