Debangshu Banerjee
CS PhD Student @ UIUC
I am a 3rd year PhD student in the Computer Science department at the University of Illinois, Urbana-Champaign. I work at the intersection of machine learning and formal methods to develop next-generation programming systems with provable correctness. I am presently advised by Prof. Gagandeep Singh.
I am currently looking into the development of programming systems with LLMs that provide users with finer-grained control over the generated output, such as code and logical formulas. On the theoretical side, I am interested in investigating the capabilities and potential limitations of LLMs in understanding code semantics. Previously, my research focused on neural network verification and certifiable training, where I developed the first scalable GPU-accelerated verification and training method for relational properties, including monotonicity and robustness against universal adversarial perturbations (UAPs).