PhD Candidate
UC Berkeley
Areas of Interest
- Artificial Intelligence
- Programming Systems
- Security
Poster
Deep Learning for Program Synthesis from Diverse Specifications
Abstract
My main research focus is neural program synthesis, where I propose deep learning techniques to synthesize programs from different specifications. So far, the complexity of the synthesized programs by existing approaches is still limited. Therefore, my main research goal is to synthesize programs with higher complexity and better generalizability.
I have developed deep learning techniques to better leverage syntactic and semantic information of programs. Specifically, I have been working on: (1) translating natural language descriptions to programs; (2) program synthesis from input-output examples; and (3) leveraging deep learning techniques for software engineering applications.
Bio
Xinyun Chen is a Ph.D. student at UC Berkeley, working with Prof. Dawn Song. Her research lies at the intersection of deep learning, programming languages, and security. Her recent research focuses on neural program synthesis and adversarial machine learning, towards tackling the grand challenges of increasing the accessibility of programming to general users, and enhancing the security and trustworthiness of machine learning models. She received the Facebook Fellowship in 2020.
