Sherlock4Py
🔎🐛 Sherlock4Py 🐍 MaxSAT-Based Misbehaviour Verification and Localisation Framework for Python Sherlock4Py is a research project investigating how formal reasoning and Large …
Research Topics
My research explores Neuro-symbolic AI, focusing on the synergy between Automated Reasoning (AR) and Machine Learning (ML) to enhance the robustness and reliability of ML models, including Large Language Models and Vision–Language Models.
I investigate these challenges across diverse reasoning tasks, with applications including logical reasoning, code understanding, and AI for Software Engineering (AI4SE).
Below is a selection of research topics I have explored over the years.
Neuro-Symbolic AI for Reliable Reasoning
Modern foundation models, including Large Language Models (LLMs) and Vision-Language Models (VLMs), have remarkable capabilities for understanding natural language, code, and …
Artificial Intelligence for Reliable Code
Understanding the reasoning and robustness of AI systems, such as Large Language Models (LLMs), is critical for ensuring their reliable use in programming tasks. While recent …
Model-Based Diagnosis for Software
Localising system faults has long been recognised as one of the most time-consuming and costly tasks in software engineering. Given a buggy system, fault localisation (FL) refers …
Artificial Intelligence for CS Education
Empowering the next generation of programmers requires intelligent systems that not only evaluate code but also teach, guide, and inspire. This research explores how Artificial …
Automated Assessment Tools for Programming Education
Delivering personalised, scalable feedback to students in large programming courses remains one of the most persistent challenges in Computer Science and Software Engineering …
Automated Feedback for Introductory Programming Exercises
Delivering valuable and personalised feedback to students remains one of the greatest challenges in programming education, particularly in courses with large enrollments. Providing …
User partitioning for Maximum Satisfiability
The Maximum Satisfiability (MaxSAT) problem is the optimisation variant of the Satisfiability (SAT) problem. Solving MaxSAT efficiently often involves partitioning the set of soft …
Query Reverse Engineering
Many data analysts are domain experts but lack programming expertise. While they can describe what transformation they want to perform, they often struggle to express it in a query …