Artificial Intelligence for Codign Assistance

Coding Assistance refers to automated tools that help with developer tasks like code completion, bug detection, etc, like the ones we get access to using our favorite IDEs like IntelliJ or Eclipse. Recently, there has been a surge of research in utilizing Artificial Intelligence, especially Deep neural networks and Transformers to assist with code completion. The most famous manifestation of this is the Copilot project from GitHub. However, these approaches also have similar challenges primarily because they rely on code in the wild to learn. Code written by human beings in the wild has its issues like bugs, vulnerabilities, and privacy concerns. In this context, it is of paramount importance to understand the state of the art in the field of AI for Code Intelligence and work on future research.

With a group of max. 8 participants, we will explore current scientific work from the area of applying AI for CA under the guidance of the lecturer firsts. Then you will form smaller subgroups and conceptualize improvements to the state of the art, which you will write down in the form of a small vision paper. Details on the available topics will be announced at the first event.