I am an Assistant Professor in Computer Science and Engineering and an affiliate of the Science & Justice Research Center and the Generative AI Center at UC Santa Cruz. I am part of the AI group @ UCSC and I lead the AI Explainability and Accountability (AIEA) Lab.
Previously, I was a research scientist at Sony AI working on explainability in AI agents. I graduated with my PhD in Electrical Engineering and Computer Science at MIT in CSAIL, where I continue as a collaborating researcher. During my PhD, I developed “Anomaly Detection through Explanations” or ADE, a self-explaining, full system monitoring architecture to detect and explain inconsistencies in autonomous vehicles. This allows machines and other complex mechanisms to be able to interpret their actions and learn from their mistakes.
My research focuses on the theories and methodologies towards monitoring, designing, and augmenting complex machines that can explain themselves for diagnosis, accountability, and liability. My long-term research vision is for self-explaining, intelligent, machines by design.
Read more about my approach to communication, collaboration, and mentoring on the Working With Me page.
PhD in Electrical Engineering and Computer Science, 2020
Massachusetts Institute of Technology
M.S. in Computational and Mathematical Engineering, 2013
Stanford University
BSc in Computer Science, BSc in Mathematics, Music minor, 2011
UC San Diego
Featured talks are available as videos.
Combining the flexibility of LLMs with the rigor of symbolic reasoning to generate faithful neuro-symbolic reasoning for high-stakes use cases.
Using symbolic language and neuro-symbolic AI for legal applications.
Understanding what knowledge AI systems learn and where they store it in their neurons.
Applying explainable AI methods to mental-health settings.
An explainable assessment tool or autograder for CSE courses.
Understanding and explaining failures such as hallucinations in large language models.
Detecting and explaining errors and failures in autonomous vehicles.
The AI and ethics reading group is a student-led, campus-wide initiative.
Using internal symbolic, explanatory representations to robustly monitor agents.
An adaptable framework to supplement decision-making systems with commonsense knowledge and reasonableness rules.
The methodologies and underlying technologies that allow self-driving cars and other AI-driven systems to explain behaviors and failures.
Note: This is a working list. It is inspired by my colleague. Let’s pass it along.