AI Coders Are among Us: Rethinking Programming Language Grammar towards Efficient Code Generation

Speaker: Dr. Xiaoning Du
Monash University

Title: AI Coders Are among Us: Rethinking Programming Language Grammar towards Efficient Code Generation

Date: Monday, 10 February 2025

Time: 4:00pm - 5:00pm

Venue: Lecture Theater F (Leung Yat Sing Lecture Theater), near lift 25/26, HKUST

Abstract:

AI models have emerged as another important audience for programming languages alongside humans and machines as we enter the era of LLMs. LLMs can now perform well in coding competitions and even write programs like developers to solve various tasks, including mathematical problems. However, the grammar and layout of current programs are designed to cater to the needs of human developers -- with many grammar tokens and formatting tokens being used to make the code easier for humans to read. While this is helpful, such a design adds unnecessary computational work for LLMs, as each token they use or produce consumes computational resources. In this talk, I will share an initial attempt at redesigning the Python grammar for more efficient and green code LLMs.

Biography:

Dr. Du Xiaoning is a Lecturer (a.k.a. Assistant Professor in the US) at the Faculty of Information Technology, Monash University. She received her Ph.D. from Nanyang Technological University in 2020 and her Bachelor's degree from Fudan University in 2014. Her research is dedicated to devising innovative, intelligent techniques for various software engineering tasks while promoting responsible development and adoption of code intelligence. Her research has been published in top-tier conferences and journals and has attracted the attention of many industrial practitioners of code language models. Her work has won or been nominated for the ACM SIGSOFT Distinguished Paper Award multiple times. She also received the 2024 FIT Dean's Early Career Researcher of the Year Award and the 2024 Google Research Scholar Award.