Advanced Research in Software Engineering

AI models are increasingly being used in safety-critical systems like autonomous vehicles. This comes with the concerns about the quality and reliability of these systems, as several erroneous and sometimes even fatal behaviors have already been reported. However, due to the fundamental architectural differences between AI and traditional software, existing software testing techniques do not apply to them in an obvious way. In fact, companies like Google, Tesla, etc. are increasingly facing all the traditional software testing challenges. To this end, we aim to develop a testing framework for detecting erroneous behaviors for AI systems. So far, we have found thousands of erroneous behaviors in award-winning self-driving car models, many of which could lead to potentially fatal crashes.

At the ARiSE Lab, we conduct research at the intersection of Artificial Intelligence and Software Engineering, with a core focus on AI for Code. Our mission is to develop neurosymbolic techniques that combine the adaptability of machine learning with the rigor of formal reasoning to improve software reliability, security, and developer productivity.

​

We build intelligent systems—ranging from language models to autonomous developer agents—that can understand, generate, and repair code in a principled and scalable way. By designing new abstractions and learning frameworks grounded in program semantics, we aim to make software not just easier to write, but fundamentally easier to trust.

​

We maintain active industry collaboration with companies like IBM, Google, Microsoft, Amazon, Redhat.