Si Chen

Modeling action unit relationships can dramatically enhance facial expression recognition across diverse domains, leading to substantial performance gains.

Adversarial images in CLIP reveal a consistent directional bias that can be exploited to enhance model robustness, leading to surprising cases where adversarial accuracy surpasses clean accuracy.

As AI increasingly shapes STEM career paths for students, this workshop identifies critical design tensions and governance principles for ensuring responsible and equitable AI-driven career development tools.