Hao Fang

APEX improves how robots work with two arms for complex tasks.

New method reveals vulnerabilities in Vision-Language Pre-training models through universal adversarial perturbations.

H-GLaD enhances dataset distillation, improving efficiency and performance in model training.

A novel method enhances adversarial attacks in machine learning models using CLIP.

Teams compete to improve methods for predicting video attention.

A new method to create efficient synthetic datasets for deep learning models.