Page Not Found
Page not found. Your pixels are in another canvas. Read more
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Page not found. Your pixels are in another canvas. Read more
Contact me Read more
This is a page not in the main menu Read more
Published:
How to Measure and Maximise Developer Productivity Read more
Published:
Subtle ways to not make gender diversity a discrimination. Read more
Published:
Thoughts on different ways to improve Code Quality Read more
Published:
History of DevOps, continuous software engineering practices in industry and continous software engineering research perspectives Read more
Published:
What are types of missing data in datasets and How to Handle Missing Data in Datasets Read more
Published:
Short description of portfolio item number 1
Read more
Published:
Short description of portfolio item number 2
Read more
Published in University of Victoria, 2022
AI-supported programming has arrived, as shown by the introduction and successes of large language models for code, such as Copilot/Codex (Github/OpenAI) and AlphaCode (DeepMind). Above-average human performance on programming challenges is now possible. However, software development is much more than solving programming contests. Moving beyond code completion to AI-supported software development will require an AI system that can, among other things, understand how to avoid code smells, follow language idioms, and eventually (maybe!) propose rational software designs. Read more
Recommended citation: Rohith Pudari. "AI Supported Software Development: Moving Beyond Code Completion," Msc Thesis, Department of Computer Science, University of Victoria., Victoria, BC, 2022. [Online]. Available: http://hdl.handle.net/1828/14155 http://hdl.handle.net/1828/14155
Published in The International Conference on Software Maintenance and Evolution (ICSME) 2023 (NIER track), 2023
Stack Overflow (SO) is a widely used question-and- answer (Q&A) forum dedicated to software development. It plays a supplementary role to official documentation (DOC for short) by offering practical examples and resolving uncertainties. However, the process of simultaneously consulting both the documentation and SO posts can be challenging and time-consuming due to their disconnected nature. In this study, we propose DOSA, a novel approach to automatically align SO and DOC, which inject domain-specific knowledge about the DOC structure into large language models (LLMs) through weak supervision and constrained decoding, thereby enhancing knowledge retrieval and streamlining task completion during the software development procedure. Our preliminary experiments find that DOSA outperforms various widely-used baselines, showing the promise of using generative retrieval models to perform low-resource software engineering tasks. Read more
Published:
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown! Read more
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post. Read more
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post. Read more