Loris D'Antoni

Loris D'Antoni is an Associate Professor in the Department of Computer Science and Engineering at the University of California at San Diego (UCSD). He also holds a visiting academic position at AWS. His research focuses on helping people write trustworthy software through advances in programming languages, program verification, and synthesis techniques.

• Education: Bachelor's and Master's degrees in Computer Science from the University of Torino (2008-2010); PhD in Computer Science from the University of Pennsylvania (2015).

His research interests span programming languages, formal verification, program synthesis, automata theory, and trustworthy machine learning systems. Recent work includes developing frameworks for semantics-guided synthesis (SemGuS), formal verification of fairness in machine learning, and methods for constraining large language models of code.

Recent publications address topics like access control policy analysis, grammar-constrained decoding for language models, and automated specification synthesis. These works intersect computer science, formal methods, and machine learning.

Awarded multiple prestigious accolades including the NSF CAREER Award, Microsoft Research Faculty Fellowship, and Google Faculty Award, he has also received the Morris and Dorothy Rubinoff Dissertation Award and was a Phillip R. Certain-Gary D. Sandefur Distinguished Faculty Award recipient.

D'Antoni advises PhD students including Keith Johnson, Shaan Nagy, Jinwoo Kim, and Kanghee Park. Former advisees like Yuhao Zhang, Qinheping Hu, and Kausik Subramanian have moved on to prominent roles at companies such as Amazon, Google, and Facebook.

He leads the Programming Systems Group at UCSD and collaborates with AWS on specification-aligned LLMs. His work also involves tools like AutomataTutor for education and projects at the intersection of program synthesis and machine learning robustness.