ECE Seminar Series: Lily Weng
The Department of Electrical and Computer Engineering presents its seminar series featuring guest speaker Lily Weng, assistant professor in the Halıcıoğlu Data Science Institute at University of California San Diego, who will present “Toward Trustworthy AI: Automated Interpretability, Adversarial Robustness, and AI Safety.” This seminar will take place on Friday, March 6, from 12:45–1:45 p.m. over Zoom.
Abstract
Deep learning models have become remarkably powerful—but often operate as black boxes. In this talk, I will share how my lab is making these systems more transparent, reliable, and trustworthy. I’ll highlight three research directions to bring interpretability into deep learning: (1) automated tools [1-4] that reveal what neural networks learn internally at scale; (2) inherently interpretable neural model architectures [5–8] that make model’s decision process more understandable and controllable; and (3) evaluation frameworks [9–12] that quantify interpretability and enable trust. I’ll also touch on our work [13–16] in jailbreak attacks on LLMs, robustness verification, and robust learning for safer artificial intelligence deployment. Together, these efforts aim to move modern AI beyond accuracy—toward systems we can truly understand, align, and trust. For more details, please visit .
Biography
Lily Weng is an assistant professor in the Halıcıoğlu Data Science Institute at University of California San Diego with affiliation in the CSE department. She received her Ph.D. in electrical engineering and computer science (EECS) from MIT in August 2020, and her bachelor’s and master’s degree both in electrical engineering at National Taiwan University. Prior to UCSD, she spent one year in MIT-IBM Watson AI Lab and several research internships in Google DeepMind, IBM Research, and Mitsubishi Electric Research Lab. Her research interest is in machine learning and deep learning, with primary focus on trustworthy AI. Her vision is to make the next generation of AI systems and deep learning algorithms more robust, reliable, explainable, trustworthy, and safer. Her work has been recognized and supported by several NSF awards, ARL award, Intel Rising Star Faculty Award, Hellman Fellowship, and Nvidia Academic award.