Yu-Shuen Wang

Quality and Diversity Optimization Even From Offline Homogeneous Dataset

Actively Enlarging Feature Norms with Universal Adversarial Training and Channel Calibration for Superior OOD Detection

Unconstrained Models as Constrained Problem Solvers: Duality-Driven Adaptation without Retraining

Learn out of the box: optimizing both diversity and performance in Offline Reinforcement Learning

Pseudo-Labels are All You Need for Out-Of-Distribution Detection