Shiyu Chang

Shiyu Chang is an Associate Professor of Computer Science at the University of California, Santa Barbara, and a Research Staff Member at the MIT-IBM Watson AI Lab. His work bridges machine learning, natural language processing, and computer vision with a focus on interpretability and robustness.

• Current Affiliation: UC Santa Barbara
• Lab: MIT-IBM Watson AI Lab

His research explores how to make AI systems more interpretable and robust by integrating human intuition and rationalization. Key themes include adversarial learning, self-supervised methods, and improving transferability in models.

Recent publications span conferences like ICML, CVPR, and NeurIPS, addressing topics such as black-box text classification, fairness-aware algorithms, and speech representation disentanglement. Broad keywords include Machine Learning, NLP, and Computer Vision.

• Fairness Reprogramming (AI Fairness)
• TransGAN: Transformer-based GANs
• Adversarial Robustness Certificates