Publications/Tools

• A full list of publications is available on my Google scholar.

Tools/Benchmarks

• TARGET: A tool that leverages pre-trained code language models (CLMs) for automated test case repair
• TARBENCH: A comprehensive benchmark, including 45,373 repaired broken tests across 59 open-source projects
• PRBatch: A dataset containing around 0.6 million comments linked to approximately 66,000 pull requests on GitHub
• TCP-CI: A benchmark of 25 subjects with 21.5k builds and 2.5k failed builds
• TP-RL: A reinforcement learning-based tool for test case prioritization
• UMLRTSynthesizer: A behavioural model synthesizer
• MDETools: A website with a search capability determining which model transformation tools support a given set of features
• SimGen: A tool for generating simulations and visualizations of embedded systems on the unity game engine
• PMExec: A tool that supports the execution of partial UML-RT models

Theses

• Artin Biniek Diss. Bidirectional Generation of Behavior-Driven Development Artifacts Using Fine-Tuning and Retrieval-Augmented Generation. Carleton University, 2026.
• Paniz Oghabi Diss. Multi-Label Ambiguity Detection in Software Requirements Using Language Models. Carleton University, 2025.
• Darren Holden. Leveraging Language Models to Improve Code Quality Through Code Linting and Automated Test Repair. Diss. Carleton University, 2024.
• Arvin Samiei. Black-Box Worst Case Execution Time Analysis on Real-Time Robotic Algorithms. Diss. Carleton University, 2024.
• Chibuike Ejikeme. Optimizing Distributed Denial of Service (DDoS) Detection with Time Series Transformers. Diss. Carleton University, 2023.
• Joshi, Rinkesh. Reinforcement Learning for GitHub Pull Request Predictions: Analyzing Development Dynamics. Diss. Carleton University, 2023.