Programming Assistance
Programming assistance, encompassing automated code generation and debugging, aims to improve coding efficiency and accessibility across various domains. Current research focuses on leveraging large language models (LLMs) to provide code suggestions, generate code from natural language prompts, and even refine training data for improved model performance. This rapidly evolving field holds significant implications for scientific research, education, and software development by accelerating workflows, lowering the barrier to entry for programming, and enhancing code quality and security.
Papers
Students' Perceptions and Preferences of Generative Artificial Intelligence Feedback for Programming
Zhengdong Zhang, Zihan Dong, Yang Shi, Noboru Matsuda, Thomas Price, Dongkuan Xu
Primitive-based 3D Human-Object Interaction Modelling and Programming
Siqi Liu, Yong-Lu Li, Zhou Fang, Xinpeng Liu, Yang You, Cewu Lu
Multi-Intent Detection in User Provided Annotations for Programming by Examples Systems
Nischal Ashok Kumar, Nitin Gupta, Shanmukha Guttula, Hima Patel
Copilot for Xcode: Exploring AI-Assisted Programming by Prompting Cloud-based Large Language Models
Chee Wei Tan, Shangxin Guo, Man Fai Wong, Ching Nam Hang